tangshitao

MVDiffusion. MVDiffusion: Enabling Holistic Multi-view Image Generation with Correspondence-Aware Diffusion, NeurIPS 2023 (spotlight)

QuadTreeAttention. QuadTree Attention for Vision Transformers (ICLR2022)

MVDiffusion_plusplus. MVDiffusion++: A Dense High-resolution Multi-view Diffusion Model for Single or Sparse-view 3D Object Reconstruction

ClipShots. ClipShots is the first large-scale dataset for shot boundary detection collected from Youtube and Weibo covering more than 20 categories, including sports, TV shows, animals, etc.

Dense-Scene-Matching. Learning Camera Localization via Dense Scene Matching, CVPR2021

ClipShots_basline. This is our implementation of deepSBD for ClipShots dataset.

NeuMap. NeuMap: Neural Coordinate Mapping by Auto-Transdecoder for Camera Localization, CVPR2023

Semi-supervised-Adaptive-Distillation. Semi-supervised Adaptive Distillation is a model compression method for object detection.

CENet. Channel Equilibrium Networks for Learning Deep Representation, ICML2020

TSP-genetic-algorithm-and-Christofides-algorithm. solving TSP problem using genetic algorithm and Christofides algorithm

SIFT. SIFT implementation require opencv

HarrisCornerDetection_gpu.

HarrisCornerDetection_cpu.