Publiczne ślady GitHub ARC Lab, Tencent PCG

GFPGAN aims at developing Practical Algorithms for Real-world Face Restoration.

PhotoMaker [CVPR 2024]

InstantMesh: Efficient 3D Mesh Generation from a Single Image with Sparse-view Large Reconstruction Models

T2I-Adapter

[SIGGRAPH 2026] Pixal3D: Pixel-Aligned 3D Generation from Images

[ECCV 2024] The official implementation of paper "BrushNet: A Plug-and-Play Image Inpainting Model with Decomposed Dual-Branch Diffusion"

Official Code for MotionCtrl [SIGGRAPH 2024]

SEED-Voken: A Series of Powerful Visual Tokenizers

SEED-Story: Multimodal Long Story Generation with Large Language Model

[ICCV 2023] Consistent Image Synthesis and Editing

[SIGGRAPH2025] Official repo for paper "Any-length Video Inpainting and Editing with Plug-and-Play Context Control"

[under review] The official implementation of paper "BrushEdit: All-In-One Image Inpainting and Editing"

[ICLR 2026] Streamlining Cartoon Production with Generative Post-Keyframing

[ACL 2024] Progressive LLaMA with Block Expansion.

A framework to convert any 2D videos to immersive stereoscopic 3D

The official implementation of paper "ColorFlow: Retrieval-Augmented Image Sequence Colorization". ColorFlow：基于检索增强的图像序列上色

[ICCV 2025] GeometryCrafter: Consistent Geometry Estimation for Open-world Videos with Diffusion Priors

NeurIPS 2023, Mix-of-Show: Decentralized Low-Rank Adaptation for Multi-Concept Customization of Diffusion Models

[ICLR 2026] Official Repo for Rolling Forcing: Autoregressive Long Video Diffusion in Real Time

VerseCrafter: Dynamic Realistic Video World Model with 4D Geometric Control

Official code of SmartEdit [CVPR-2024 Highlight]

Codes for "AnimeSR: Learning Real-World Super-Resolution Models for Animation Videos"

ECCV 2022, Oral, VQFR: Blind Face Restoration with Vector-Quantized Dictionary and Parallel Decoder

[ICCV 2025] AnimeGamer: Infinite Anime Life Simulation with Next Game State Prediction

[CVPR 2025] Official code of "DiTCtrl: Exploring Attention Control in Multi-Modal Diffusion Transformer for Tuning-Free Multi-Prompt Longer Video Generation"

AudioStory: Generating Long-Form Narrative Audio with Large Language Models

Brak opisu dla tego repozytorium.

[ICCV 2025] FreeSplatter: Pose-free Gaussian Splatting for Sparse-view 3D Reconstruction

UMT is a unified and flexible framework which can handle different input modality combinations, and output video moment retrieval and/or highlight detection results.

Structured Video Comprehension of Real-World Shorts

TokLIP: Marry Visual Tokens to CLIP for Multimodal Comprehension and Generation

Track4World: Feedforward World-centric Dense 3D Tracking of All Pixels

[CVPR 2024] ViT-Lens: Towards Omni-modal Representations

Codes for "Metric Learning based Interactive Modulation for Real-World Super-Resolution"

[ICCV2025 Oral] Latent Motion Token as the Bridging Language for Learning Robot Manipulation from Videos

[CVPR 2026 Highlight🔥] MotionCrafter: Dense Geometry and Motion Reconstruction with a 4D VAE

[ICLR'26] IC-Custom: Diverse Image Customization via In-Context Learning

[ICLR 2026] GenCompositor: Generative Video Compositing with Diffusion Transformer

[ECCV 2024🔥] Official implementation of the paper "ST-LLM: Large Language Models Are Effective Temporal Learners"

[CVPR 2026] TimeLens: Rethinking Video Temporal Grounding with Multimodal LLMs

Official codes for DeSRA (ICML 2023)

Official code for "Bridging Video-text Retrieval with Multiple Choice Questions", CVPR 2022 (Oral).

[NeurIPS2025] The official implementation of MindOmni: Unleashing Reasoning Generation in Vision Language Models with RGPO

Code release of our paper "DI-PCG: Diffusion-based Efficient Inverse Procedural Content Generation for High-quality 3D Asset Creation".

[CVPR 2025] Boosting Generative Novel View Synthesis with Sparse and Unposed Images

[CVPR 2026] Spatio-Temporal Autoregressive 4K 360° Video Generation from Perspective Video

NeurIPS 2021, Spotlight, Finding Discriminative Filters for Specific Degradations in Blind Super-Resolution

Brak opisu dla tego repozytorium.

Nerf and extensions in all

Brak opisu dla tego repozytorium.

mllm-npu: training multimodal large language models on Ascend NPUs

Video-Holmes: Can MLLM Think Like Holmes for Complex Video Reasoning?

Diffusion Powers Video Tokenizer for Comprehension and Generation (CVPR 2025)

[ACL2026 Findings] GRPO-CARE: Consistency-Aware Reinforcement Learning for Multimodal Reasoning

SurfelNeRF: Neural Surfel Radiance Fields for Online Photorealistic Reconstruction of Indoor Scenes

Codes for "RepSR: Training Efficient VGG-style Super-Resolution Networks with Structural Re-Parameterization and Batch Normalization"

Brak opisu dla tego repozytorium.

HOSNeRF: Dynamic Human-Object-Scene Neural Radiance Fields from a Single Video

Codes for "Mitigating Artifacts in Real-World Video Super-Resolution Models"

Official code for "What Makes for Good Visual Tokenizers for Large Language Models?".

Official codes for ConMIM (ICLR 2023)

Turning to Video for Transcript Sorting

Official code for "Binary embedding based retrieval at Tencent"

Structuring Hour-Long Videos into Navigable Chapters and Hierarchical Summaries

Brak opisu dla tego repozytorium.

[IJCAI 2023] official implementation of the paper SGAT4PASS: Spherical Geometry-Aware Transformer for PAnoramic Semantic Segmentation

Official code for "pi-Tuning: Transferring Multimodal Foundation Models with Optimal Multi-task Interpolation", ICML 2023.

BTS: A Bi-lingual Benchmark for Text Segmentation in the Wild

Accelerating Vision-Language Pretraining with Free Language Modeling (CVPR 2023)

Codes for "Accelerating the Training of Video Super-Resolution"

Official code for "Dynamic Token Normalization Improves Vision Transformer", ICLR 2022.

OpenCompatible provides a standard compatible training benchmark, covering practical training scenarios.

Brak opisu dla tego repozytorium.

[SIGGRAPH ASIA'25] BlobCtrl: Taming Controllable Blob for Element-level Image Editing

Brak opisu dla tego repozytorium.

OmniScript: Towards Audio-Visual Script Generation for Long-Form Cinematic Video

Official code for the paper, "TaCA: Upgrading Your Visual Foundation Model with Task-agnostic Compatible Adapter".

Common template for pytorch project. Easy to extent and modify for new project.

The code repo for the ACM MM paper: TransFusion: Multi-Modal Fusion for Video Tag Inference viaTranslation-based Knowledge Embedding.

Visualization of 3d and 2d components interactively.

Brak opisu dla tego repozytorium.

Brak opisu dla tego repozytorium.

Sculpt4D: Generating 4D Shapes via Sparse-Attention Diffusion Transformers. CVPR‘2026

vllm for ARC-Hunyuan-Video-7B

Brak opisu dla tego repozytorium.

An optical flow forward warp's lib with backpropagation using pytorch.