Related papers: Motion2VecSets: 4D Latent Vector Set Diffusion for…

Microstructure reconstruction, a major component of inverse computational materials engineering, is currently advancing at an unprecedented rate. While various training-based and training-free approaches are developed, the majority of…

Mesh reconstruction from multi-view images is a fundamental problem in computer vision, but its performance degrades significantly under sparse-view conditions, especially in unseen regions where no ground-truth observations are available.…

We propose a diffusion model designed to generate point-based shape representations with correspondences. Traditional statistical shape models have considered point correspondences extensively, but current deep learning methods do not take…

We present TexFusion (Texture Diffusion), a new method to synthesize textures for given 3D geometries, using large-scale text-guided image diffusion models. In contrast to recent works that leverage 2D text-to-image diffusion models to…

Object pose estimation from a single view remains a challenging problem. In particular, partial observability, occlusions, and object symmetries eventually result in pose ambiguity. To account for this multimodality, this work proposes…

Video frame prediction extrapolates future frames from previous frames, but suffers from prediction errors in dynamic scenes due to the lack of information about the next frame. Event cameras address this limitation by capturing per-pixel…

The world around us is full of soft objects we perceive and deform with dexterous hand movements. For a robotic hand to control soft objects, it has to acquire online state feedback of the deforming object. While RGB-D cameras can collect…

Directly reconstructing 3D CT volume from few-view 2D X-rays using an end-to-end deep learning network is a challenging task, as X-ray images are merely projection views of the 3D CT volume. In this work, we facilitate complex 2D X-ray…

We present LTM3D, a Latent Token space Modeling framework for conditional 3D shape generation that integrates the strengths of diffusion and auto-regressive (AR) models. While diffusion-based methods effectively model continuous latent…

Denoising diffusion models have demonstrated outstanding results in 2D image generation, yet it remains a challenge to replicate its success in 3D shape generation. In this paper, we propose leveraging multi-view depth, which represents…

Text-based image segmentation aims to delineate object boundaries within an image from text prompts, offering higher flexibility and broader application scope compared to traditional fixed-category segmentation tasks. Recent studies have…

The motion transfer task aims to transfer motion from a source video to newly generated videos, requiring the model to decouple motion from appearance. Previous diffusion-based methods primarily rely on separate spatial and temporal…

Diffusion models have established themselves as state-of-the-art generative models across various data modalities, including images and videos, due to their ability to accurately approximate complex data distributions. Unlike traditional…

Lossy compression relies on an autoencoder to transform a point cloud into latent points for storage, leaving the inherent redundancy of latent representations unexplored. To reduce redundancy in latent points, we propose a diffusion-based…

Reconstructing high-quality point clouds from images remains challenging in computer vision. Existing generative-model-based approaches, particularly diffusion-model approaches that directly learn the posterior, may suffer from…

Recent advances in diffusion transformers have shown remarkable generalization in visual synthesis, yet most dense perception methods still rely on text-to-image (T2I) generators designed for stochastic generation. We revisit this paradigm…

Latent space is one of the key concepts in generative AI, offering powerful means for creative exploration through vector manipulation. However, diffusion models like Stable Diffusion lack the intuitive latent vector control found in GANs,…

Geological parameterization entails the representation of a geomodel using a small set of latent variables and a mapping from these variables to grid-block properties such as porosity and permeability. Parameterization is useful for data…

Diffusion Models (DMs) have demonstrated state-of-the-art performance in content generation without requiring adversarial training. These models are trained using a two-step process. First, a forward - diffusion - process gradually adds…

We introduce a new general-purpose approach to deep learning on 3D surfaces, based on the insight that a simple diffusion layer is highly effective for spatial communication. The resulting networks are automatically robust to changes in…