Research
A paper is listed when one of its authors is affiliated with the lab. Data: OpenAlex.
Pose Priors from Language ModelsGoogle DeepMind · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings7 citationsJun 10, 2025OmniSplat: Taming Feed-Forward 3D Gaussian Splatting for Omnidirectional Images with Editable CapabilitiesLG AI Research · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings7 citationsJun 10, 2025Segment Anything, Even OccludedNVIDIA · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings7 citationsJun 10, 2025Unleashing In-context Learning of Autoregressive Models for Few-shot Image ManipulationMeta · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings7 citationsJun 10, 2025Cropper: Vision-Language Model for Image Cropping through In-Context LearningAlphabet, Google DeepMind · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings7 citationsJun 10, 2025Learning from Streaming Video with Orthogonal GradientsGoogle DeepMind · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings6 citationsJun 10, 2025HMAR: Efficient Hierarchical Masked Auto-Regressive Image GenerationNVIDIA · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings6 citationsJun 10, 2025LookCloser: Frequency-aware Radiance Field for Tiny-Detail SceneSenseTime · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings6 citationsJun 10, 2025VideoComp: Advancing Fine-Grained Compositional and Temporal Alignment in Video-Text ModelsGoogle DeepMind · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings6 citationsJun 10, 2025Can Generative Video Models Help Pose Estimation?Alphabet · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings6 citationsJun 10, 2025A Simple yet Effective Layout Token in Large Language Models for Document UnderstandingAlibaba · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings6 citationsJun 10, 2025Boltzmann Attention Sampling for Image Analysis with Small ObjectsMicrosoft · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings6 citationsJun 10, 2025LIRM: Large Inverse Rendering Model for Progressive Reconstruction of Shape, Materials and View-dependent Radiance FieldsMeta · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings6 citationsJun 10, 2025Zero-Shot RGB-D Point Cloud Registration with Pre-Trained Large Vision ModelAlibaba · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings6 citationsJun 10, 2025VideoMage: Multi-Subject and Motion Customization of Text-to-Video Diffusion ModelsNVIDIA · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings6 citationsJun 10, 2025From Sparse Signal to Smooth Motion: Real-Time Motion Generation with Rolling Prediction ModelsMeta · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings6 citationsJun 10, 2025SceneCrafter: Controllable Multi-View Driving Scene EditingGoogle DeepMind · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings6 citationsJun 10, 2025AMO Sampler: Enhancing Text Rendering with OvershootingAlphabet · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings6 citationsJun 10, 2025UNICL-SAM: Uncertainty-Driven In-Context Segmentation with Part Prototype DiscoveryMicrosoft · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings6 citationsJun 10, 2025UNIC-Adapter: Unified Image-Instruction Adapter with Multi-Modal Transformer for Image GenerationAlibaba · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings6 citationsJun 10, 2025Omni-RGPT: Unifying Image and Video Region-level Understanding via Token MarksNVIDIA · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings6 citationsJun 10, 2025PICD: Versatile Perceptual Image Compression with Diffusion RenderingMicrosoft · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings6 citationsJun 10, 2025Harnessing Frozen Unimodal Encoders for Flexible Multimodal AlignmentTechnology Innovation Institute · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings6 citationsJun 10, 2025Unsupervised Continual Domain Shift Learning with Multi-Prototype ModelingSenseTime · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings5 citationsJun 10, 2025SoundVista: Novel-View Ambient Sound Synthesis via Visual-Acoustic BindingMeta · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings5 citationsJun 10, 2025