Research
A paper is listed when one of its authors is affiliated with the lab. Data: OpenAlex.
Motion Prompting: Controlling Video Generation with Motion TrajectoriesGoogle DeepMind · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings37 citationsJun 10, 2025A Bias-Free Training Paradigm for More General AI-generated Image DetectionGoogle DeepMind · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings28 citationsJun 10, 2025VLOGGER: Multimodal Diffusion for Embodied Avatar SynthesisGoogle DeepMind · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings16 citationsJun 10, 20253D-GSW: 3D Gaussian Splatting for Robust WatermarkingGoogle DeepMind · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings14 citationsJun 10, 2025Stereo4D: Learning How Things Move in 3D from Internet Stereo VideosGoogle DeepMind · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings12 citationsJun 10, 2025Flexible Frame Selection for Efficient Video ReasoningGoogle DeepMind · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings11 citationsJun 10, 2025Simpler Diffusion: 1.5 FID on ImageNet512 with pixel-space diffusionAlphabet, Google DeepMind · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings11 citationsJun 10, 2025Good, Cheap, and Fast: Overfitted Image Compression with Wasserstein DistortionGoogle DeepMind · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings8 citationsJun 10, 2025DynamicScaler: Seamless and Scalable Video Generation for Panoramic ScenesGoogle 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, 2025Calibrated Multi-Preference Optimization for Aligning Diffusion ModelsAlphabet, Google 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, 2025Tuning the Frequencies: Robust Training for Sinusoidal Neural NetworksGoogle DeepMind · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings5 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/Proceedings5 citationsJun 10, 2025Token Cropr: Faster ViTs for Quite a Few TasksGoogle DeepMind · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings5 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/Proceedings4 citationsJun 10, 2025Active Data Curation Effectively Distills Large-Scale Multimodal ModelsAlphabet, Google DeepMind · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings4 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/Proceedings3 citationsJun 10, 2025Chapter-Llama: Efficient Chaptering in Hour-Long Videos with LLMsGoogle DeepMind · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings3 citationsJun 10, 2025Generative Omnimatte: Learning to Decompose Video into LayersGoogle DeepMind · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings3 citationsJun 10, 2025Pose 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/Proceedings3 citationsJun 10, 2025Language-Guided Image Tokenization for GenerationGoogle DeepMind · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings3 citationsJun 10, 2025Learning Visual Composition through Improved Semantic GuidanceGoogle DeepMind · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings2 citationsJun 10, 2025Context-Aware Multimodal PretrainingGoogle DeepMind · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings2 citationsJun 10, 2025SimVS: Simulating World Inconsistencies for Robust View SynthesisAlphabet, Google DeepMind · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings2 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/Proceedings2 citationsJun 10, 2025Visual Lexicon: Rich Image Features in Language SpaceGoogle DeepMind · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings1 citationJun 10, 2025