05:43

GraphDreamer: Compositional 3D Scene Synthesis from Scene Graphs

04:27

Mip-Splatting: Alias-free 3D Gaussian Splatting

02:27

HUGS: Holistic Urban 3D Scene Understanding via Gaussian Splatting

01:31

Efficient End-to-End Detection of 6-DoF Grasps for Robotic Bin Picking

02:48

PlanT: Explainable Planning Transformers via Object-Level Representations

27:06

Constraining 3D Fields for Reconstruction and View Synthesis

29:44

Learning Robust Policies for Self-Driving

21:37

Generating Images and 3D Shapes

04:55

ARAH: Animatable Volume Rendering of Articulated Human SDFs

04:41

KING: Generating Safety-Critical Driving Scenarios for Robust Imitation via Kinematics Gradients

03:44

KING: Generating Safety-Critical Driving Scenarios for Robust Imitation via Kinematics Gradients

06:43

ARAH: Animatable Volume Rendering of Articulated Human SDFs

04:39

gDNA: Towards Generative Detailed Neural Avatars

10:36

On the Frequency Bias of Generative Models

09:13

MetaAvatar: Learning Animatable Clothed Human Models from Few Depth Images

14:51

ATISS: Autoregressive Transformers for Indoor Scene Synthesis

06:00

CAMPARI: Camera-Aware Decomposed Generative Neural Radiance Fields

12:38

Shape As Points: A Differentiable Poisson Solver

03:05

CAMPARI: Camera-Aware Decomposed Generative Neural Radiance Fields

32:33

Driving with Attention

28:29

Towards Animatable Human Avatars

33:57

STEP: Segmenting and Tracking Every Pixel

25:38

Generative Neural Scene Representationsfor 3D-Aware Image Synthesis

23:28

KITTI-360: A Novel Dataset and Benchmarks for Urban Scene Understanding in 2D and 3D

11:15

UNISURF: Unifying Neural Implicit Surfaces and Radiance Fields for Multi-View Reconstruction

11:59

SLIM: Self-Supervised LiDAR Scene Flow and Motion Segmentation

05:00

SNARF: Differentiable Forward Skinning for Animating Non-Rigid Neural Implicit Shapes

05:01

NEAT: Neural Attention Fields for End-to-End Autonomous Driving

03:41

KiloNeRF: Speeding up Neural Radiance Fields with Thousands of Tiny MLPs

02:00

SLIM: Self-Supervised LiDAR Scene Flow and Motion Segmentation

06:27

SNARF: Differentiable Forward Skinning for Animating Non-Rigid Neural Implicit Shapes

02:00

UNISURF: Unifying Neural Implicit Surfaces and Radiance Fields for Multi-View Reconstruction

02:35

NEAT: Neural Attention Fields for End-to-End Autonomous Driving

01:30

KiloNeRF: Speeding up Neural Radiance Fields with Thousands of Tiny MLPs

12:08

Learning Cascaded Detection Tasks with Weakly-Supervised Domain Adaptation

11:02

CVPR 2021 - AVG Remix

03:59

Locally Aware Piecewise Transformation Fields for 3D Human Mesh Registration

05:00

Neural Parts: Learning Expressive 3D Shape Abstractions with Invertible Neural Networks

05:19

SMD-Nets: Stereo Mixture Density Networks

06:01

Multi-Modal Fusion Transformer for End-to-End Autonomous Driving

06:11

GIRAFFE: Representing Scenes as Compositional Generative Neural Feature Fields

03:30

Neural Parts: Learning Expressive 3D Shape Abstractions with Invertible Neural Networks

00:48

Locally Aware Piecewise Transformation Fields for 3D Human Mesh Registration

04:14

Locally Aware Piecewise Transformation Fields for 3D Human Mesh Registration

01:38

Multi-Modal Fusion Transformer for End-to-End Autonomous Driving

02:16

GIRAFFE: Representing Scenes as Compositional Generative Neural Feature Fields

01:36

Counterfactual Latent Dance

03:01

GRAF: Generative Radiance Fields for 3D-Aware Image Synthesis

51:50

Yash Sharma: Towards Nonlinear Disentanglement in Natural Data with Temporal Sparse Coding

02:49

GRAF: Generative Radiance Fields for 3D-Aware Image Synthesis

51:14

Sai Bi: Appearance Acquisition for Digital 3D Content Creation

02:28

KITTI-360

51:03

Manmohan Chandraker: Physically-Motivated Learning of Shape, Material and Lighting in Complex Scenes

01:56:15

RVC 2020 - Live Session 1

01:45:18

RVC 2020 - Live Session 2

04:52

RVC 2020 - Introduction

27:50

RVC 2020 - Keynote: Ross Girshick - Robustness Across the Data Abundance Spectrum

18:57

RVC 2020 - Keynote: Quoc Viet Le - Noisy Student Training for Robust Vision

46:15

RVC 2020 - Keynote: Aleksander Madry - What Do Our Models Learn?

00:43

RVC 2020 - Epilogue