Accepted Papers


The list of accepted 3DV papers is now available!

Download list of accepted papers



Oral Session 1: Humans & Non-Rigid Shapes


Chaired by
Torsten Sattler
1
MoCapDeform: Monocular 3D Human Motion Capture in Deformable Scenes

Zhi Li, Soshi Shimada, Bernt Schiele, Christian Theobalt and Vladislav Golyanik

In Person - Poster [A1]

2
Long Term Motion Prediction Using Keyposes

Sena Kiciroglu , Wei Wang, Mathieu Salzmann and Pascal Fua

In Person - Poster [A2]

3
Garment Ideation: Iterative view-aware sketch-based garment modeling

Pinaki Nath Chowdhury, Tuanfeng Wang, Duygu Ceylan, Yi-Zhe Song and Yulia Gryaditskaya

In Person - Poster [A3]

4
Spectral Teacher for a Spatial Student: Spectrum-Aware Real-Time Dense Shape Correspondence

Omri Efroni, Dan Raviv and Dvir Ginzburg

In Person - Poster [A4]

Spotlight 1 / Poster 1


Chaired by
Djamila Aouada and Zhaopeng Cui
1
Point Discriminative Learning for Data-efficient 3D Point Cloud Analysis

Fayao Liu, Guosheng Lin, Chuan Sheng Foo, Chaitanya K Joshi and Jie Lin

Virtual

3
Adjoint Rigid Transform Network: Task-conditioned Alignment of 3D Shapes

Keyang Zhou, Bharat Lal Bhatnagar, Bernt Schiele and Gerard Pons-Moll

In Person - Poster [A5]

4
ACDet: Attentive Cross-view Fusion for LiDAR-based 3D Object Detection

Guowei Wan, jiaolong xu, Guojun Wang and xiao zhang

Virtual

5
ManiFlow: Implicitly Representing Manifolds with Normalizing Flows

Janis Postels, Martin Danelljan, Luc Van Gool and Federico Tombari

In Person - Poster [A6]

6
SphereDepth: Panorama Depth Estimation from Spherical Domain

Qingsong Yan, Qiang Wang, Kaiyong Zhao, Bo Li, Xiaowen Chu and Fei Deng

Virtual

7
Efficient Human Pose Estimation via 3D Event Point Cloud

Jiaan Chen, Hao Shi, Yaozu Ye, Kailun Yang, Lei Sun and Kaiwei Wang

Virtual

8
CADOps-Net: Jointly Learning CAD Operation Types and Steps from Boundary-Representations

Elona Dupont, Kseniya Cherenkova, Anis Kacem, Sk Aziz Ali, Ilya Arzhannikov, Gleb A Gusev and Djamila Aouada

In Person - Poster [B1]

9
Push-the-Boundary: Boundary-aware Feature Propagation for Semantic Segmentation of 3D Point Clouds

Shenglan Du, Nail Ibrahimli, Jantien Stoter, Julian F P Kooij and Liangliang Nan

In Person - Poster [B2]

10
Distortion-aware Depth Estimation with Gradient Priors from Panoramas of Indoor Scenes

Ruihong Yin, Sezer Karaoglu and Theo Gevers

In Person - Poster [B3]

11
SRFeat: Learning Locally Accurate and Globally Consistent Non-Rigid Shape Correspondence

Lei Li, Souhaib Attaiki and Maks Ovsjanikov

Virtual

Spotlight 2 / Poster 1


Chaired by
Oleksandr Shekhovtsov and Armin Mustafa
1
The 8-Point Algorithm as an Inductive Bias for Relative Pose Prediction by ViTs

Chris Rockwell, Justin Johnson and David Fouhey

In Person - Poster [B4]

2
GNPM: Self-Supervised Geometric-Aware Neural Parametric Model

Mirgahney H Mohamed and Lourdes Agapito

In Person - Poster [B5]

3
Keypoint Cascade Voting for Point Cloud Based 6DoF Pose Estimation

Yangzheng Wu, Alireza Javaheri, Mohsen Zand and Michael Alan Greenspan

Virtual

4
There and Back Again: 3D Mesh Sequence Generation from Text Using Back-Translation

Stephanie M Stoll, Armin Mustafa and Jean-Yves Guillemaut

Virtual

5
HVTR: Hybrid Volumetric-Textural Rendering for Human Avatars

Tao Hu, Tao Yu, Zerong Zheng, He Zhang, Yebin Liu and Matthias Zwicker

Virtual

6
The Surprising Positive Knowledge Transfer in Continual 3D Object Shape Reconstruction

Anh Thai, Stefan Stojanov, Zixuan Huang and James Rehg

In Person - Poster [B6]

7
Human Body Measurement Estimation with Adversarial Augmentation

Nataniel Ruiz, Miriam Bellver, Timo Bolkart, Ming C Lin, Javier Romero and Raja Bala

Virtual

8
Progressive Multi-scale Light Field Networks

David Li and Amitabh Varshney

In Person - Poster [B7]

Oral Session 2: (Neural) Scene Representations & Point Clouds


Chaired by
Torsten Sattler
1
GO-Surf: Neural Feature Grid Optimization for Fast, High-Fidelity RGB-D Surface Reconstruction

Jingwen Wang, Tymoteusz Bleja and Lourdes Agapito

In Person - Poster [A1]

2
Neural Feature Fusion Fields: 3D Distillation of Self-Supervised 2D Image Representations

Vadim Tschernezki, Iro Laina, Diane Larlus and Andrea Vedaldi

In Person - Poster [A2]

3
Dimensions of Motion: Monocular Prediction through Flow Subspaces

Richard S Bowen, Richard Tucker, Ramin Zabih and Noah Snavely

In Person - Poster [A3]

4
Arbitrary Point Cloud Upsampling with Spherical Mixture of Gaussians

Anthony Dell'Eva, Marco Orsingher and Massimo Bertozzi

In Person - Poster [A4]

5
Guided Co-Modulated GAN for 360° Field of View Extrapolation

Mohammad Reza Karimi Dastjerdi, Yannick Hold-Geoffroy, Jonathan Eisenmann, Siavash Khodadadeh and Jean-Francois Lalonde

In Person - Poster [A5]

Spotlight 3 / Poster 2


Chaired by
Jinwei Ye and Yiyi Liao
1
MonoNHR: Monocular Neural Human Renderer

Hongsuk Choi, Gyeongsik Moon, Matthieu Armando, Vincent Leroy, Kyoung Mu Lee and Gregory Rogez

In Person - Poster [A6]

2
Simultaneous Localisation and Mapping with Quadric Surfaces

Tristan Laidlow and Andrew Davison

Virtual

3
Domain Adaptive 3D Pose Augmentation for In-the-wild Human Mesh Recovery

Zhenzhen Weng, Kuan-Chieh Wang, Angjoo Kanazawa and Serena Yeung

Virtual

4
SHRAG: Semantic Hierarchical Graph for Floorplan Representation

Jin Jiongchao, Zhou Xue and Biao Leng

Virtual

5
SO(3) Rotation Equivariant Point Cloud Completion using Attention-based Vector Neurons

Hang Wu and Yubin Miao

Virtual

6
High-speed and Low-latency 3D Sensing with a Parallel-bus Pattern

Leo Miyashita, Satoshi Tabata and Masatoshi Ishikawa

In Person - Poster [B1]

7
Panoptic NeRF: 3D-to-2D Label Transfer for Panoptic Urban Scene Segmentation

Xiao Fu, Shangzhan Zhang, Tianrun Chen, Yichong Lu, Lanyun Zhu, Xiaowei Zhou, Andreas Geiger and Yiyi Liao

Virtual

8
Articulated 3D Human-Object Interactions from RGB Videos: An Empirical Analysis of Approaches and Challenges

Sanjay Haresh, Xiaohao Sun, Hanxiao Jiang, Angel X Chang and Manolis Savva

Virtual

Spotlight 4 / Poster 2


Chaired by
Čeněk Albl and Or Litany
1
A Flexible Multi-view Multi-modal Imaging System for Large-Scale Outdoor Scenes

Meng Zhang, Wenxuan Guo, Bohao Fan, Yifan Chen, Jianjiang Feng and Jie Zhou

Virtual

2
Cut-and-Paste Object Insertion by Enabling Deep Image Prior for Reshading

Anand Bhattad and David Forsyth

In Person - Poster [B2]

3
3INGAN: Learning a 3D Generative Model from Images of a Self-similar Scene

Animesh Karnewar, Oliver Wang, Tobias Ritschel and niloy mitra

In Person - Poster [B3]

4
Reconstructing Action-Conditioned Human-Object Interactions Using Commonsense Knowledge Priors

Xi Wang, Gen Li, Yen-Ling Kuo, Muhammed Kocabas, Emre Aksan and Otmar Hilliges

In Person - Poster [B4]

5
Dual-Space NeRF: Learning Animatable Avatars and Scene Lighting in Separate Spaces

Yihao Zhi, Shenhan Qian, Xinhao Yan and Shenghua Gao

Virtual

6
Fast Gradient Descent for Surface Capture Via Differentiable Rendering

Briac Toussaint, Maxime Genisson and Jean-Sebastien Franco

In Person - Poster [B5]

7
Structure-Aware 3D VR Sketch to 3D Shape Retrieval

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

In Person - Poster [B6]

8
Visual Localization via Few-Shot Scene Region Classification

Siyan Dong, Shuzhe Wang, Yixin Zhuang, Juho Kannala, Marc Pollefeys and Baoquan Chen

In Person - Poster [C1]

9
Robust RGB-D Fusion for Saliency Detection

Zongwei WU, Shriarulmozhivarman Gobichettipalayam, Brahim Tamadazte, Guillaume Allibert, Danda Pani Paudel and Cedric Demonceaux

In Person - Poster [C2]

10
Temporal Action Composition for Human Bodies

Nikos Athanasiou, Mathis Petrovich, Michael J. Black and Gul Varol

In Person - Poster [C3]

11
Temporal Shape Transfer Network for 3D Human Motion

Joao Pedro Cova Regateiro and Edmond Boyer

In Person - Poster [C4]

Oral Session 3: Shapes, Objects, & Views


Chaired by
Tomas Pajdla
1
SDA-SNE: Spatial Discontinuity-Aware Surface Normal Estimation via Multi-Directional Dynamic Programming

Nan Ming, Yi Feng and Rui R. Fan

Virtual

2
Smooth Non-Rigid Shape Matching via Effective Dirichlet Energy Optimization

Robin Magnet, Jing Ren, Olga Sorkine-Hornung and Maks Ovsjanikov

In Person - Poster [A1]

3
Bidirectional Feature Globalization for Few-shot Semantic Segmentation of 3D Point Cloud Scenes

Yongqiang Mao, Zonghao Guo, Xiaonan Lu, Zhiqiang Yuan and Haowen Guo

Virtual

4
PIZZA: A Powerful Image-only Zero-Shot Zero-CAD Approach to 6DoF Tracking

Van Nguyen NGUYEN, Yuming Du, Yang Xiao, Michaël Ramamonjisoa and Vincent Lepetit

In Person - Poster [A2]

5
Any-Shot GIN: Generalizing Implicit Networks for Reconstructing Novel Classes

Yongqin Xian, Julian Chibane, Bharat Lal Bhatnagar, Zeynep Akata, Bernt Schiele and Gerard Pons-Moll

Virtual

Spotlight 5 / Poster 3


Chaired by
Jiri Sedlar and Federico Tombari
1
SC6D: Symmetry-agnostic and Correspondence-free 6D Object Pose Estimation

Dingding Cai, Janne Heikkila and Esa Rahtu

In Person - Poster [A3]

2
SVNet: Where SO(3) Equivariance Meets Binarization on Point Cloud Representation

Zhuo Su, Max Welling, Matti Pietikäinen and Li Liu

In Person - Poster [A4]

3
A Structured Latent Space for Human Body Motion Generation

Mathieu S Marsot, Stefanie Wuhrer, Jean-Sebastien Franco and Stephane Durocher

In Person - Poster [A5]

4
gCoRF: Generative Compositional Radiance Fields

Mallikarjun B R, Ayush Tewari, Xingang Pan, Mohamed Elgharib and Christian Theobalt

In Person - Poster [A6]

5
On Triangulation as a Form of Self-Supervision for 3D Human Pose Estimation

SOUMAVA KUMAR ROY, Leonardo Citraro, Sina Honari and Pascal Fua

In Person - Poster [B1]

6
Pose Guided Human Motion Transfer by Exploiting 2D and 3D Information

Yahui Zhang, Shaodi You, Sezer Karaoglu and Theo Gevers

In Person - Poster [B2]

7
HoW-3D: Holistic 3D Wireframe Perception from a Single Image

Wenchao Ma, Bin Tan, Nan Xue, Tianfu Wu, Xianwei Zheng and Gui-Song Xia

Virtual

8
Cross-Spectral Neural Radiance Fields

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

In Person - Poster [B3]

9
HybridSDF: Combining Deep Implicit Shapes and Geometric Primitives for 3D Shape Representation and Manipulation

Subeesh Vasu, Nicolas Talabot, Artem Lukoianov, Pierre Baque, Jonathan Donier and Pascal Fua

In Person - Poster [B4]

10
TempCLR: Reconstructing Hands via Time-Coherent Contrastive Learning

Andrea Ziani, Zicong Fan, Muhammed Kocabas, Sammy Christen and Otmar Hilliges

Virtual

11
LC-NAS: Latency Constrained Neural Architecture Search for Point Cloud Networks

Guohao Li , Mengmeng Frost Xu, Silvio Giancola, Ali K Thabet and Bernard Ghanem

In Person - Poster [B5]

12
A Benchmark and a Baseline for Robust Multi-view Depth Estimation

Philipp Schröppel, Thomas Brox, Artemij Amiranashvili and Jan Bechtold

In Person - Poster [B6]

Spotlight 6 / Poster 3


Chaired by
Zuzana Kukelova and Zan Gojcic
1
Controllable Radiance Fields for Dynamic Face Synthesis

Peiye Zhuang, Liqian Ma, Sanmi Koyejo and Alexander Schwing

Virtual

2
Benchmarking Pedestrian Odometry: The Brown Pedestrian Odometry Dataset (BPOD)

David Charatan, Hongyi Fan and Benjamin Kimia

Virtual

3
MonoViT: Self-Supervised Monocular Depth Estimation with a Vision Transformer

Chaoqiang Zhao, Youmin Zhang, Matteo Poggi, Fabio Tosi, xianda guo, Zheng Zhu, Guan Huang, Yang Tang and Stefano Mattoccia

In Person - Poster [B7]

4
Neural Point-based Shape Modeling of Humans in Challenging Clothing

Qianli Ma, Jinlong Yang, Michael J. Black and Siyu Tang

In Person - Poster [C1] (Virtual Presentation)

5
Polar-Photometric Stereo Under Natural Illumination

Yuqi Ding, Yu Ji and Jinwei Ye

In Person - Poster [C2]

6
Interactive Sketching of Mannequin Poses

Gizem E Unlu, Mohamed Sayed and Gabriel Brostow

In Person - Poster [C3]

7
GAN2X: Non-Lambertian Inverse Rendering of Image GANs

Xingang Pan, Ayush Tewari, Lingjie Liu and Christian Theobalt

In Person - Poster [C4]

8
OoD-Pose: Camera Pose Regression from Out-of-Distribution Synthetic Views

Tony Ng, Adrian Lopez-Rodriguez, Vasileios Balntas and Krystian Mikolajczyk

Virtual







  Important Dates

All deadlines are 23:59 Pacific Time (PT). No extensions will be granted.

Paper registration May 26 June 2, 2022
Paper submission June 2, 2022
Supplementary June 9, 2022
Tutorial submission August 15, 2022
Rebuttal period July 8-14 10-15, 2022
Paper notification July 31, 2022
Camera ready Sept 1, 2022
Demo submission August 15, 2022
Tutorial September 12, 2022
Main conference September 12-15, 2022