Research
A paper is listed when one of its authors is affiliated with the lab. Data: OpenAlex.
Controllable Weather Synthesis and Removal with Video Diffusion ModelsNVIDIA · IEEE/CVF International Conference on Computer Vision (ICCV)14 citationsOct 19, 2025LongSplat: Robust Unposed 3D Gaussian Splatting for Casual Long VideosNVIDIA · IEEE/CVF International Conference on Computer Vision (ICCV)14 citationsOct 19, 20252.5 Years in Class: A Multimodal Textbook for Vision-Language PretrainingAlibaba · IEEE/CVF International Conference on Computer Vision (ICCV)14 citationsOct 19, 2025Erasing More Than Intended? How Concept Erasure Degrades the Generation of Non-Target ConceptsAlphabet, Google DeepMind · IEEE/CVF International Conference on Computer Vision (ICCV)13 citationsOct 19, 2025Preacher: Paper-to-Video Agentic SystemAlibaba · IEEE/CVF International Conference on Computer Vision (ICCV)13 citationsOct 19, 2025MCBLT: Multi-Camera Multi-Object 3D Tracking in Long VideosNVIDIA · IEEE International Conference on Computer Vision Workshops13 citationsOct 19, 2025I2V3D: Controllable Image-to-Video Generation with 3D GuidanceMicrosoft · IEEE/CVF International Conference on Computer Vision (ICCV)13 citationsOct 19, 2025FreeFlux: Understanding and Exploiting Layer-Specific Roles in RoPE-Based MMDiT for Versatile Image EditingMicrosoft · IEEE/CVF International Conference on Computer Vision (ICCV)13 citationsOct 19, 2025Low-Light Image Enhancement Using Event-Based Illumination EstimationAlibaba · IEEE/CVF International Conference on Computer Vision (ICCV)13 citationsOct 19, 2025ObjectMate: A Recurrence Prior for Object Insertion and Subject-Driven GenerationAlphabet · IEEE/CVF International Conference on Computer Vision (ICCV)13 citationsOct 19, 2025Magic Insert: Style-Aware Drag-And-DropAlphabet, Google DeepMind · IEEE/CVF International Conference on Computer Vision (ICCV)13 citationsOct 19, 2025From One to More: Contextual Part Latents for 3D GenerationSenseTime · IEEE/CVF International Conference on Computer Vision (ICCV)12 citationsOct 19, 2025Back on Track: Bundle Adjustment for Dynamic Scene ReconstructionMicrosoft · IEEE/CVF International Conference on Computer Vision (ICCV)12 citationsOct 19, 2025DPoser-X: Diffusion Model as Robust 3D Whole-Body Human Pose PriorNVIDIA, SenseTime · IEEE/CVF International Conference on Computer Vision (ICCV)12 citationsOct 19, 2025WikiAutoGen: Towards Multi-Modal Wikipedia-Style Article GenerationMeta · IEEE/CVF International Conference on Computer Vision (ICCV)11 citationsOct 19, 2025OmniCache: A Trajectory-Oriented Global Perspective on Training-Free Cache Reuse for Diffusion Transformer ModelsZhipu AI · IEEE/CVF International Conference on Computer Vision (ICCV)11 citationsOct 19, 2025MeshLLM: Empowering Large Language Models to Progressively Understand and Generate 3D MeshAlphabet · IEEE/CVF International Conference on Computer Vision (ICCV)11 citationsOct 19, 2025DocThinker: Explainable Multimodal Large Language Models with Rule-Based Reinforcement Learning for Document UnderstandingAlibaba · IEEE/CVF International Conference on Computer Vision (ICCV)11 citationsOct 19, 2025HERMES: Temporal-Coherent Long-form Understanding with Episodes and SemanticsNVIDIA · IEEE/CVF International Conference on Computer Vision (ICCV)11 citationsOct 19, 2025JointDiT: Enhancing RGB-Depth Joint Modeling with Diffusion TransformersMicrosoft · IEEE/CVF International Conference on Computer Vision (ICCV)10 citationsOct 19, 2025AirCache: Activating Inter-Modal Relevancy KV Cache Compression for Efficient Large Vision-Language Model InferenceAlibaba · IEEE/CVF International Conference on Computer Vision (ICCV)10 citationsOct 19, 2025SAM4D: Segment Anything in Camera and LiDAR StreamsAlibaba · IEEE/CVF International Conference on Computer Vision (ICCV)10 citationsOct 19, 2025MPG-SAM 2: Adapting SAM 2 with Mask Priors and Global Context for Referring Video Object SegmentationHorizon Robotics · IEEE/CVF International Conference on Computer Vision (ICCV)10 citationsOct 19, 2025Spectral Image TokenizerAlphabet · IEEE/CVF International Conference on Computer Vision (ICCV)10 citationsOct 19, 2025DIVE: Taming DINO for Subject-Driven Video EditingNVIDIA · IEEE/CVF International Conference on Computer Vision (ICCV)10 citationsOct 19, 2025