PlaneTR3D[ICCV'21] PlaneTR: Structure-Guided Transformers for 3D Plane Recovery
MVP BenchmarkMVP Benchmark for Multi-View Partial Point Cloud Completion and Registration
neat[ICCV'21] NEAT: Neural Attention Fields for End-to-End Autonomous Driving
dti-sprites(ICCV 2021) Code for "Unsupervised Layered Image Decomposition into Object Prototypes" paper
CurveNetOfficial implementation of "Walk in the Cloud: Learning Curves for Point Clouds Shape Analysis", ICCV 2021
HCFlowOfficial PyTorch code for Hierarchical Conditional Flow: A Unified Framework for Image Super-Resolution and Image Rescaling (HCFlow, ICCV2021)
QmapCompressionOfficial implementation of "Variable-Rate Deep Image Compression through Spatially-Adaptive Feature Transform", ICCV 2021
snarfOfficial code release for ICCV 2021 paper SNARF: Differentiable Forward Skinning for Animating Non-rigid Neural Implicit Shapes.
PoinTr[ICCV 2021 Oral] PoinTr: Diverse Point Cloud Completion with Geometry-Aware Transformers
cycle-confusionCode and models for ICCV2021 paper "Robust Object Detection via Instance-Level Temporal Cycle Confusion".
gnerf[ ICCV 2021 Oral ] Our method can estimate camera poses and neural radiance fields jointly when the cameras are initialized at random poses in complex scenarios (outside-in scenes, even with less texture or intense noise )
ilvr admILVR: Conditioning Method for Denoising Diffusion Probabilistic Models (ICCV 2021 Oral)
renet[ICCV'21] Official PyTorch implementation of Relational Embedding for Few-Shot Classification
PCLocPose Correction for Highly Accurate Visual Localization in Large-scale Indoor Spaces (ICCV 2021)
DeepCADcode for our ICCV 2021 paper "DeepCAD: A Deep Generative Network for Computer-Aided Design Models"
retrieval-fuse[ICCV21] Code for "RetrievalFuse: Neural 3D Scene Reconstruction with a Database"
USOT[ICCV2021] Learning to Track Objects from Unlabeled Videos
STTranSpatial-Temporal Transformer for Dynamic Scene Graph Generation, ICCV2021
TRAR-VQA[ICCV 2021] TRAR: Routing the Attention Spans in Transformers for Visual Question Answering -- Official Implementation
C5Reference code for the paper "Cross-Camera Convolutional Color Constancy" (ICCV 2021)
flow1d[ICCV 2021 Oral] High-Resolution Optical Flow from 1D Attention and Correlation
InstanceRefer[ICCV 2021] InstanceRefer: Cooperative Holistic Understanding for Visual Grounding on Point Clouds through Instance Multi-level Contextual Referring
MSRGCNOfficial implementation of MSR-GCN (ICCV2021 paper)
LLVIPLLVIP: A Visible-infrared Paired Dataset for Low-light Vision
SnowflakeNet(TPAMI 2022) Snowflake Point Deconvolution for Point Cloud Completion and Generation with Skip-Transformer
G-SFDAcode for our ICCV 2021 paper 'Generalized Source-free Domain Adaptation'