Accepted Papers

Oral Session 1: 3D Human Analysis

Chaired by
Dimitrios Tzionas and Stefanos Zafeiriou


Learning To Disambiguate Strongly Interacting Hands via Probabilistic Per-pixel Part Segmentation

Zicong Fan, Adrian Spurr, Muhammed Kocabas, Siyu Tang, Michael J. Black and Otmar Hilliges



Body Size and Depth Disambiguation in Multi-Person Reconstruction from Single Images

Nicolas Ugrinovic, Adria Ruiz, Antonio Agudo, Alberto Sanfeliu and Francesc Moreno



A Skeleton-Driven Neural Occupancy Representation for Articulated Hands

Korrawe Karunratanakul, Adrian Spurr, Zicong Fan, Otmar Hilliges and Siyu Tang



Exemplar Fine-Tuning for 3D Human Model Fitting Towards In-the-Wild 3D Human Pose Estimation

Hanbyul Joo, Natalia Neverova and Andrea Vedaldi



RealisticHands: A Hybrid Model for 3D Hand Reconstruction

Michael Seeber, Roi Poranne, Marc Pollefeys and Martin R. Oswald



EgoGlass: Egocentric-View Human Pose Estimation from an Eyeglass Frame

Dongxu Zhao, Zhen Wei, Jisan Mahmud and Jan-Michael Frahm

Poster Spotlight 1

Chaired by
Gerard Pons-Moll


Generative Zero-Shot Learning for Semantic Segmentation of 3D Point Clouds

Bjoern Michele, Alexandre Boulch, Gilles Puy, Renaud Marlet and Maxime Bucher



Monocular 3D Reconstruction of Interacting Hands via Collision-Aware Factorized Refinements

Yu Rong, Jingbo Wang, Ziwei Liu and Chen Change Loy



Investigating Attention Mechanism in 3D Point Cloud Object Detection

Shi Qiu, Yunfan Wu, Saeed Anwar and Chongyi Li



Semi-supervised 3D Object Detection via Temporal Graph Neural Networks

Jianren Wang, Haiming Gang, Siddharth Ancha, Yi-Ting Chen and David Held



Stochastic Neural Radiance Fields: Quantifying Uncertainty in Implicit 3D Representations

Jianxiong Shen, Adria Ruiz, Antonio Agudo and Francesc Moreno



CAMPARI: Camera-Aware Decomposed Generative Neural Radiance Fields

Michael Niemeyer and Andreas Geiger



Event Guided Depth Sensing

Manasi Muglikar, Diederik Paul Moeys and Davide Scaramuzza



3D Lip Event Detection via Interframe Motion Divergence at Multiple Temporal Resolutions

Jie Zhang and Robert B Fisher



Deep Physics-aware Inference of Cloth Deformation for Monocular Human Performance Capture

Yue Li, Marc Habermann, Bernhard Thomaszewski, Stelian Coros, Thabo Beeler and Christian Theobalt



NeeDrop: Self-supervised Shape Representation from Sparse Point Clouds using Needle Dropping

Alexandre Boulch, Pierre-Alain Langlois, Gilles Puy and Renaud Marlet



Fine-Grained VR Sketching: Dataset and Insights.

Ling Luo, Yulia Gryaditskaya, Yongxin Yang, Tao Xiang and Yi-Zhe Song



L2D2: Learnable Line Detector and Descriptor

Hichem Abdellali, Robert Frohlich, Viktor Vilagos and Zoltan Kato



PolyNet: Polynomial Neural Network for 3D Shape Recognition with PolyShape Representation

Mohsen Yavartanoo, Shih-Hsuan Hung, Reyhaneh Neshatavar, Yue Zhang and Kyoung Mu Lee



Point2FFD: Learning Shape Representations of Simulation-ready 3D Models for Engineering Design Optimization

Thiago Rios, Bas van Stein, Thomas Bäck, Bernhard Sendhoff and Stefan Menzel



3D-MetaConNet: Meta-learning for 3D Shape Classification and Segmentation

Hao Huang, Xiang Li, Lingjing Wang and Yi Fang



Leveraging Spatial and Photometric Context for Calibrated Non-Lambertian Photometric Stereo

David Honzátko, Engin Türetken, Pascal Fua and L. Andrea Dunbar



FiG-NeRF: Figure-Ground Neural Radiance Fields for 3D Object Category Modelling

Christopher Xie, Keunhong Park, Ricardo Martin-Brualla and Matthew Brown

Oral Session 2: 3D Modelling and Synthesis

Chaired by
Jean-Francois Lalonde and Hamid Laga


Mix3D: Out-of-Context Data Augmentation for 3D Scenes

Alexey Nekrasov, Jonas Schult, Or Litany, Bastian Leibe and Francis Engelmann



PoseContrast: Class-Agnostic Object Viewpoint Estimation in the Wild with Pose-Aware Contrastive Learning

Yang Xiao, Yuming Du and Renaud Marlet



GenIcoNet: Generative Icosahedral Mesh Convolutional Network

Hardik Jain and Olaf Hellwich



DiffSDFSim: Differentiable Rigid-Body Dynamics with Implicit Shapes

Michael Strecke and Joerg Stueckler



SceneFormer: Indoor Scene Generation with Transformers

Chandan Yeshwanth, Xinpeng Wang and Matthias Niessner



3D Reconstruction of Novel Object Shapes from Single Images

Anh Thai, Stefan Stojanov, Vijay Upadhya and James Rehg

Poster Spotlight 2

Chaired by
Silvia Zuffi


Recovering Real-world Reflectance Properties and Shading from HDR Imagery

Bjoern Haefner, Simon Green, Alan Oursland, Daniel Andersen, Michael Goesele, Daniel Cremers, Richard Newcombe and Thomas Whelan



NVSS: High-quality Novel View Selfie Synthesis

Jia-Wang Bian, Huangying Zhan and Ian Reid



Projective Urban Texturing

Yiangos Georgiou, Melinos Averkiou, Tom Kelly and Evangelos Kalogerakis



Attacking Image Classifiers To Generate 3D Textures

Camilo Andres Pestana and Ajmal Mian



Channel-wise Attention-based Network for Self-Supervised Monocular Depth Estimation

Jiaxing Yan, Hong Zhao, Penghui Bu and Yusheng Jin



MP-Mono: Monocular 3D Detection Using Multiple Priors for Autonomous Driving

Pei Liu, Guorun Yang, Peixuan Li, Zhe Wang, Jianping Shi, Zhidong Deng and Yu Qiao



Synergy between 3DMM and 3D Landmarks for Accurate 3D Facial Geometry

Cho-Ying Wu, Qiangeng Xu and Ulrich Neumann



AIR-Nets: An Attention-Based Framework for Locally Conditioned Implicit Representations

Simon Giebenhain and Bastian Goldluecke



Data-Driven 3D Reconstruction of Dressed Humans from Sparse Views

Pierre Zins, Yuanlu Xu, Edmond Boyer, Stefanie Wuhrer and Tony Tung



TermiNeRF: Ray Termination Prediction for Efficient Neural Rendering

Martin Piala and Ronald Clark



Curiosity-driven 3D Object Detection Without Labels

David Griffiths, Jan Boehm and Tobias Ritschel



SVMAC: Unsupervised 3D Human Pose Estimation from a Single Image with Single-view-multi-angle Consistenty

Yicheng Deng, Cheng Sun, Jiahui Zhu and Yongqi Sun



Representing Shape Collections with Alignment-Aware Linear Models

Romain Loiseau, Tom Monnier, loic landrieu and Mathieu Aubry



Deep Multi-View Stereo Gone Wild

François Darmon, Bénédicte Bascle, Jean-Clément Devaux, Pascal Monasse and Mathieu Aubry



Modality-Guided Subnetwork for Salient Object Detection

Zongwei WU, Guillaume Allibert, Christophe Stolz, Chao Ma and Cedric Demonceaux



RGBD-Net: Predicting Color and Depth images for Novel Views Synthesis

Phong Ha Nguyen, Animesh Karnewar, Lam Huynh, Esa Rahtu, Jiri Matas and Janne Heikkila



Softmesh: Learning Probabilistic Mesh Connectivity via Image Supervision

Eric-Tuan LE, Niloy Mitra and Iasonas Kokkinos



Joint 3D Human Shape Recovery and Pose Estimation from a Single Image with Bilayer Graph

Xin Yu, Jeroen van Baar and Siheng Chen

Oral Session 3: Acquisition and Geometry

Chaired by
Emanuele Rodola and Srikumar Ramalingam


Deep Regression on Manifolds: A 3D Rotation Case Study

Romain Brégier



MaCal -- Macro Lens Calibration and the Focus Stack Camera Model

Xiangyu Weng, Mengkun She, David Nakath and Kevin Koeser



Algebraic Constraint for Preserving Convexity of Planar Homography

Gaku Nakano



Practical Pose Trajectory Splines With Explicit Regularization

Mikael Persson, Gustav Häger, Hannes Ovren and Per-Erik Forssén



Non-Linear Anisotropic Diffusion for Memory-efficient Computed Tomography Super-Resolution Reconstruction

Khaled AbuJbara, Ramzi Idoughi and Wolfgang Heidrich



Visual Camera Re-Localization Using Graph Neural Networks and Relative Pose Supervision

Mehmet Ozgur Turkoglu, Eric Brachmann, Konrad Schindler, Gabriel Brostow and Aron Monszpart

Poster Spotlight 3

Chaired by
Shohei Nobuhara


Leveraging MoCap Data for Human Mesh Recovery

Fabien Baradel, Thibault Groueix, Philippe Weinzaepfel, Romain Brégier, Yannis Kalantidis and Gregory Rogez



Conflicts between Likelihood and Knowledge Distillation in Task Incremental Learning for 3D Object Detection

Peng YUN, Jun CEN and Ming Liu



Exploring Versatile Prior for Human Motion via Motion Frequency Guidance

Jiachen Xu, Min Wang, Jingyu Gong, Wentao Liu, Chen Qian, Yuan Xie and Lizhuang Ma



PanoDepth: A Two Stage Approach for Monocular Omnidirectional Depth Estimation

Yuyan Li, Zhixin Yan, Ye Duan and Liu Ren



Fusing Posture and Position Representations for Point Cloud-based Hand Gesture Recognition

Alexander Bigalke and Mattias Heinrich



Neural Human Deformation Transfer

Jean Basset, Adnane Boukhayma, Stefanie Wuhrer, Franck Multon and Edmond Boyer



A Spatio-temporal Transformer for 3D Human Motion Prediction

Emre Aksan, Manuel Kaufmann, Peng Cao and Otmar Hilliges



Direct-PoseNet: Absolute Pose Regression with Photometric Consistency

Shuai Chen, Zirui Wang and Victor Adrian Prisacariu



GCSR: Gray Code Super-Resolution 3D Scanning

Peter S Walecki and Gabriel Taubin



ESL: Event-based Structured Light

Manasi Muglikar, Guillermo Gallego and Davide Scaramuzza



Self-Supervised Monocular Scene Decomposition and Depth Estimation

Sadra Safadoust and Fatma Guney



Variational Monocular Depth Estimation for Reliability Prediction

Noriaki Hirose, Shun Taguchi, Keisuke Kawano and Satoshi Koide



It Is All In The Weights: Robust Rotation Averaging Revisited

Sidhartha Chitturi and Venu Madhav Govindu



Intention-based Long-Term Human Motion Anticipation

Julian Tanke, Chintan Zaveri and Jürgen Gall



Digging Into Self-Supervised Learning of Feature Descriptors

Iaroslav Melekhov, Zakaria Laskar, Xiaotian Li, Shuzhe Wang and Juho Kannala



Learning Local Recurrent Models for Human Mesh Recovery

Runze Li, Srikrishna Karanam, Ren Li, Terrence Chen, Bir Bhanu and Ziyan Wu



Ray Tracing-Guided Design of Plenoptic Cameras

Tim Michels and Reinhard Koch

Oral Session 4: Depth and Optical Flow

Chaired by
James Tompkin and Luigi Di Stefano


Monocular Depth Estimation Primed by Salient Point Detection and Normalized Hessian Loss

Lam Huynh, Matteo Pedone, Phong Ha Nguyen, Jiri Matas, Esa Rahtu and Janne Heikkila



Wild ToFu: Improving Range and Quality of Indirect Time-of-Flight Depth with RGB Fusion in Challenging Environments

HyunJun Jung, Nikolas Brasch, Ales Leonardis, Nassir Navab and Benjamin Busam



Neural Disparity Refinement for Arbitrary Resolution Stereo

Filippo Aleotti, Fabio Tosi, Pierluigi Zama Ramirez, Matteo Poggi, Samuele Salti, Stefano Mattoccia and Luigi Di Stefano



RAFT-Stereo: Multilevel Recurrent Field Transforms for Stereo Matching

Lahav O Lipson, Zachary Teed and Jia Deng



Spectral Reconstruction and Disparity from Spatio-Spectrally Coded Light Fields via Multi-Task Deep Learning

Maximilian Schambach, Jiayang Shi and Michael Heizmann



E-RAFT: Dense Optical Flow from Event Cameras

Mathias Gehrig, Mario Millhäusler, Daniel Gehrig and Davide Scaramuzza

Poster Spotlight 4

Chaired by
Shohei Nobuhara


KAMA: 3D Keypoint Aware Body Mesh Articulation

Umar Iqbal, Kevin Xie, Yunrong Guo, Jan Kautz and Pavlo Molchanov



Dynamic Multi-person Mesh Recovery from Uncalibrated Multi-view Cameras

Buzhen Huang, Yuan Shu, Tianshu Zhang and Yangang Wang



Parameterization of Ambiguity in Monocular Depth Prediction

Patrik Persson, Linn Öström, Carl Olsson and Kalle Åström



Towards Unconstrained Joint Hand-Object Reconstruction From RGB Videos

Yana Hasson, Gul Varol, Cordelia Schmid and Ivan Laptev



Learning Iterative Robust Transformation Synchronization

Zi Jian Yew and Gim Hee Lee



Self-Supervised Light Field Depth Estimation Using Epipolar Plane Images

Kunyuan Li, Jun Zhang, Jun Gao and Meibin Qi



SAFA: Structure Aware Face Animation

Qiulin Wang, Lu Zhang and Bo Li



Convex Joint Graph Matching and Clustering via Semidefinite Relaxations

Maximilian Krahn, Florian Bernard and Vladislav Golyanik



Shortest Paths in Graphs with Matrix-Valued Edges: Concepts, Algorithm and Application to 3D Multi-Shape Analysis

Viktoria Ehm, Daniel Cremers and Florian Bernard



Spatio-Temporal Human Shape Completion with Implicit Function Networks

Boyao ZHOU, Jean-Sebastien Franco, Federica Bogo and Edmond Boyer



DurLAR: A High-Fidelity 128-Channel LiDAR Dataset with Panoramic Ambient and Reflectivity Imagery for Multi-Modal Autonomous Driving Applications

Li Li, Khalid N Ismail, Hubert P. H. Shum and Toby P Breckon



3DVNet: Multi-View Depth Prediction and Volumetric Refinement

Alex N Rich, Noah Stier, Pradeep Sen and Tobias Hollerer



Geometric Adversarial Attacks and Defenses on 3D Point Clouds

Itai Lang, Uri Kotlicki and Shai Avidan



PLNet: Plane and Line Priors for Unsupervised Indoor Depth Estimation

Hualie JIANG, Laiyan Ding, Junjie Hu and Rui Huang



Direct Dense Pose Estimation

Liqian Ma, Lingjie Liu, Christian Theobalt and Luc Van Gool



R4Dyn: Exploring Radar for Self-Supervised Monocular Depth Estimation of Dynamic Scenes

Stefano Gasperini, Patrick Koch, Vinzenz Dallabetta, Nassir Navab, Benjamin Busam and Federico Tombari



Learning Residue-Aware Correlation Filters and Refining Scale Estimates for Real-Time UAV Tracking

Shuiwang Li, Yuting Liu, Qijun Zhao and Ziliang Feng

Oral Session 5: Human Modeling, Registration, and Synthesis

Chaired by
Torsten Sattler and Federico Tombari


DPFM: Deep Partial Functional Maps

Souhaib Attaiki, Gautam Pai and Maks Ovsjanikov



Dance In the Wild: Monocular Human Animation with Neural Dynamic Appearance Synthesis

Tuanfeng Wang, Duygu Ceylan, Krishna Kumar Singh and Niloy Mitra



LatentHuman: Shape-and-Pose Disentangled Latent Representations for Human Bodies

Sandro Lombardi, Bangbang Yang, Tianxing Fan, Hujun Bao, Guofeng Zhang, Marc Pollefeys and Zhaopeng Cui



Dual Mesh Convolutional Networks for Human Shape Correspondence

Nitika Verma, Adnane Boukhayma, Edmond Boyer and Jakob Verbeek



Globally Optimal Multi-Scale Monocular Hand-Eye Calibration Using Dual Quaternions

Thomas L Wodtko, Markus Horn, Michael Buchholz and Klaus Dietmayer



HumanGAN: A Generative Model of Human Images

Kripasindhu Sarkar, Lingjie Liu, Vladislav Golyanik and Christian Theobalt

Poster Spotlight 5



NeuralBlox: Real-time Neural Representation Fusion for Robust Volumetric Mapping

Stefan P Lionar, Lukas M Schmid, Cesar Cadena, Roland Siegwart and Andrei Cramariuc



Go with the Flows: Mixtures of Normalizing Flows for Point Cloud Generation and Reconstruction

Janis Postels, Mengya Liu, Riccardo Spezialetti, Luc Van Gool and Federico Tombari



Attention meets Geometry: Geometry Guided Spatial-Temporal Attention for Consistent Self-Supervised Monocular Depth Estimation

Patrick Ruhkamp, Daoyi Gao, Hanzhi Chen, Nassir Navab and Benjamin Busam



GASCN: Graph Attention Shape Completion Network

Haojie Huang, Ziyi Yang and Robert Platt



Mesh-Based Reconstruction of Dynamic Foam Images Using X-Ray CT

Jens Renders, Jan De Beenhouwer and Jan Sijbers



Multi-category Mesh Reconstruction from Image Collections

Alessandro Simoni, Stefano Pini, ROBERTO VEZZANI and Rita Cucchiara



NVS-MonoDepth: Improving Monocular Depth Prediction with Novel View Synthesis

Zuria Bauer, Zuoyue Li, Sergio Orts-Escolano, Miguel Cazorla, Marc Pollefeys and Martin R. Oswald



A Dataset-Dispersion Perspective on Reconstruction Versus Recognition in Single-View 3D Reconstruction Networks

Yefan Zhou, Yiru Shen, Yujun Yan, Chen Feng and Yaoqing Yang



High Fidelity 3D Reconstructions with Limited Physical Views

Mosam Dabhi, Chaoyang Wang, Kunal Saluja, Laszlo A Jeni, Ian Fasel and Simon Lucey



Neighborhood-based Neural Implicit Reconstruction from Point Clouds

Haiyong Jiang, Jianfei Cai, Jianmin Zheng and Jun Xiao



Task-Generic Hierarchical Human Motion Prior using VAEs

Jiaman Li, Ruben Villegas, Duygu Ceylan, Jimei Yang, Zhengfei Kuang, Hao Li and Yajie Zhao



Occlusion Guided Self-supervised Scene Flow Estimation on 3D Point Clouds

Bojun Ouyang and Dan Raviv



Dual Geometric Graph Network (DG2N) Iterative Network for Deformable Shape Alignment

Dvir Ginzburg and Dan Raviv



Collaborative Regression of Expressive Bodies using Moderation

Yao Feng, Vasileios Choutas, Timo Bolkart, Dimitrios Tzionas and Michael J. Black



Unsupervised Monocular Depth Reconstruction of Non-Rigid Scenes

Ayca Takmaz, Danda Pani Paudel, Thomas Probst, Ajad Chhatkuli, Martin R. Oswald and Luc Van Gool



SIDER: Single-Image Neural Optimization for Facial Geometric Detail Recovery

Aggelina Chatziagapi, ShahRukh Athar, Francesc Moreno-Noguer and Dimitris Samaras



HyNet: 3D Segmentation Using Hybrid Graph Networks

Bahareh Shakibajahromi, Saeed Shayestehmanesh, Daniel Schwartz and Ali Shokoufandeh



MeshMVS: Multi-View Stereo Guided Mesh Reconstruction

Rakesh Shrestha, Zhiwen Fan, Siyu Zhu, Qingkun Su, Zuozhuo Dai and Ping Tan

Oral Session 6: Reconstruction and Registration

Chaired by
Hyun Soo Park and Tony Tung


RefRec: Pseudo-labels Refinement via Shape Reconstruction for Unsupervised 3D Domain Adaptation

Adriano Cardace, Riccardo Spezialetti, Pierluigi Zama Ramirez, Samuele Salti and Luigi Di Stefano



Multi-scale Space-time Registration of Growing Plants

Haolin Pan, Julie Charlaix, Franck Hétroy-Wheeler and David Colliaux



Learning 3D Semantic Segmentation with only 2D Image Supervision

Kyle Genova, Xiaoqi Yin, Abhijit Kundu, Caroline Pantofaru, Forrester Cole, Avneesh Sud, Brian E Brewington, Brian Shucker and Thomas Funkhouser



DeepBBS: Deep Best Buddies for Point Cloud Registration

Itan Hezroni, Amnon Drory, Raja Giryes and Shai Avidan



VoRTX: Volumetric 3D Reconstruction with Transformers for Voxelwise View Selection and Fusion

Noah Stier, Alex N Rich, Pradeep Sen and Tobias Hollerer



Scalable Cluster-Consistency Statistics for Robust Multi-Object Matching

Yunpeng Shi, Shaohan Li, Tyler Maunu and Gilad Lerman

Poster Spotlight 6

Chaired by
Silvia Zuffi


4D Human Body Capture from Egocentric Video via 3D Scene Grounding

Miao Liu, Dexin Yang, Yan Zhang, Zhaopeng Cui, James Rehg and Siyu Tang



Open-set 3D Object Detection

Jun CEN, Peng YUN, Junhao CAI, Michael Yu Wang and Ming Liu



DPC: Unsupervised Deep Point Correspondence via Cross and Self Construction

Itai Lang, Dvir Ginzburg, Shai Avidan and Dan Raviv



Robust Fitting with Truncated Least Squares: A Bilevel Optimization Approach

Huu Minh Le and Christopher Zach



Efficiently Distributed Watertight Surface Reconstruction

Laurent Caraffa, Yanis Marchand, Mathieu Bredif and Bruno Vallet



Human Performance Capture from Monocular Video in the Wild

Chen Guo, Xu Chen, Jie Song and Otmar Hilliges



FLYBO: A Unified Benchmark Environment for Autonomous Flying Robots

Anthony Brunel, Amine Bourki, Oliver Strauss and Cedric Demonceaux



SUPPLE: Extracting Hand Skeleton with Spherical Unwrapping Profiles

Zimeng Zhao, Ruting Rao and Yangang Wang



Image Stitching with Locally Shared Rotation Axis

Daniel Barath, Yaqing Ding, Zuzana Kukelova and Viktor Larsson



Lifted Semantic Graph Embedding for Omnidirectional Place Recognition

Chao Zhang, Ignas Budvytis, Stephan Liwicki and Roberto Cipolla



NeuralDiff: Segmenting 3D objects that move in egocentric videos

Vadim Tschernezki, Diane Larlus and Andrea Vedaldi



Residual Geometric Feature Transform Network for 3D Surface Super-Resolution

Maolin Cui, Wuyuan Xie, Miaohui Wang and Tengcong Huang



3D Point Cloud Registration with Multi-Scale Architecture and Unsupervised Transfer Learning

Sofiane Horache, Jean-Emmanuel Deschaud and François Goulette



PhysXNet: A Customizable Approach for Learning Cloth Dynamics on Dressed People

Jordi Sanchez-Riera, Albert Pumarola and Francesc Moreno-Noguer



DSP-SLAM: Object Oriented SLAM with Deep Shape Priors

Jingwen Wang, Martin Rünz and Lourdes Agapito



Learning Scale-Adaptive Representations for Point-Level LiDAR Semantic Segmentation

Tongfeng Zhang, Kaizhi Yang and Xuejin Chen



Object SLAM-Based Active Mapping and Robotic Grasping

Yanmin Wu, 张 云洲, Delong Zhu, Xin Chen, Sonya Coleman, Wenkai Sun, Xinggang Hu and Zhiqiang Deng



3D reconstruction of insects: an improved multifocus stacking and an evaluation of learning-based MVS approaches

Chang Xu, Jiayuan Liu, Chuong Nguyen, Fabien Castan, Benoit Maujean and Simone Gasparini