4Director: Controlling Video World Models with Rigid 3D Geometry
arXiv
A video world model that uses rigid 3D geometry to control camera and object motion from a single image.
SemanTok: Predictable Semantic Tokens for Efficient Autoregressive Video Generation
arXiv
A flexible video tokenizer that puts semantics in early tokens for efficient, high-fidelity autoregressive video generation.
Arbor: Explicit Geometric Conditioning for Controllable 3D Asset Generation
arXiv
A trainable adapter for 3D generators that introduces explicit geometric control via typed constraint meshes (hull, avoidance, touch).
Stable-Layers: Fine-Tuning Image Layer Decomposition Models with VLM-Scored Reinforcement Learning
arXiv
An RL framework that fine-tunes image layer decomposition models using VLM-as-judge rewards, eliminating paired supervision.
OCTOPUS: Optimized KV Cache for Transformers via Octahedral Parametrization Under Optimal Squared Error Quantization
NeurIPS 2026
A rotation-preconditioned KV cache codec that jointly quantizes coordinate triplets via an octahedral map, achieving state-of-the-art compression across text, video, and audio modalities.
ReSWD: ReSTIR‘d, not shaken. Combining Reservoir Sampling and Sliced Wasserstein Distance for Variance Reduction.
ECCV 2026
Distribution matching is central to many vision and graphics tasks, where the widely used Wasserstein distance is too costly to compute for high dimensional distributions. The Sliced Wasserstein Distance (SWD) offers a scalable alternative, yet its Monte Carlo estimator suffers from high variance, resulting in noisy gradients and slow convergence. We introduce Reservoir SWD (ReSWD), which integrates Weighted Reservoir Sampling into SWD to adaptively retain informative projection directions in optimization steps, resulting in stable gradients while remaining unbiased. Experiments on synthetic benchmarks and real-world tasks such as color correction and diffusion guidance show that ReSWD consistently outperforms standard SWD and other variance reduction baselines.
SViM3D: Stable Video Material Diffusion for Single Image 3D Generation
In ICCV
We present Stable Video Materials 3D (SViM3D), a framework to predict multi-view consistent physically based rendering (PBR) materials, given a single image. Recently, video diffusion models have been successfully used to reconstruct 3D objects from a single image efficiently. However, reflectance is still represented by simple material models or needs to be estimated in additional pipeline steps to enable relighting and controlled appearance edits. We extend a latent video diffusion model to output spatially-varying PBR parameters and surface normals jointly with each generated RGB view based on explicit camera control. This unique setup allows for direct relighting in a 2.5D setting, and for generating a 3D asset using our model as neural prior. We introduce various mechanisms to this pipeline that improve quality in this ill-posed setting. We show state-of-the-art relighting and novel view synthesis performance on multiple object-centric datasets. Our method generalizes to diverse image inputs, enabling the generation of relightable 3D assets useful in AR/VR, movies, games and other visual media.
MARBLE: Material Recomposition and Blending in CLIP-Space
In CVPR
Editing materials of objects in images based on exemplar images is an active area of research in computer vision and graphics. We propose MARBLE, a method for performing material blending and recomposing fine-grained material properties by finding material embeddings in CLIP-space and using that to control pre-trained text-to-image models. We improve exemplar-based material editing by finding a block in the denoising UNet responsible for material attribution. Given two material exemplar-images, we find directions in the CLIP-space for blending the materials. Further, we can achieve parametric control over fine-grained material attributes such as roughness, metallic, transparency, and glow using a shallow network to predict the direction for the desired material attribute change. We perform qualitative and quantitative analysis to demonstrate the efficacy of our proposed method. We also present the ability of our method to perform multiple edits in a single forward pass and applicability to painting.
Stable Virtual Camera: Generative View Synthesis with Diffusion Models
In ICCV
We present Stable Virtual Camera (Seva), a generalist diffusion model that creates novel views of a scene, given any number of input views and target cameras. Existing works struggle to generate either large viewpoint changes or temporally smooth samples, while relying on specific task configurations. Our approach overcomes these limitations through simple model design, optimized training recipe, and flexible sampling strategy that generalize across view synthesis tasks at test time. As a result, our samples maintain high consistency without requiring additional 3D representation-based distillation, thus streamlining view synthesis in the wild. Furthermore, we show that our method can generate high-quality videos lasting up to half a minute with seamless loop closure. Extensive benchmarking demonstrates that Seva outperforms existing methods across different datasets and settings.