Related papers: Need for Speed: Zero-Shot Depth Completion with Si…

A diffusion model, which is formulated to produce an image using thousands of denoising steps, usually suffers from a slow inference speed. Existing acceleration algorithms simplify the sampling by skipping most steps yet exhibit…

Accurate three-dimensional perception is essential for modern industrial robotic systems that perform manipulation, inspection, and navigation tasks. RGB-D and stereo vision sensors are widely used for this purpose, but the depth maps they…

The dominant 3D Gaussian splatting (3DGS) acceleration methods fail to properly regulate the number of Gaussians during training, causing redundant computational time overhead. In this paper, we propose FastGS, a novel, simple, and general…

Although the diffusion model has achieved remarkable performance in the field of image generation, its high inference delay hinders its wide application in edge devices with scarce computing resources. Therefore, many training-free sampling…

Self-correction is an effective technique for maintaining parallel sampling in discrete diffusion models with minimal performance degradation. Prior work has explored self-correction at inference time or during post-training; however, such…

Diffusion models have recently emerged as a powerful approach for trajectory planning. However, their inherently non-sequential nature limits their effectiveness in long-horizon reasoning tasks at test time. The recently proposed Monte…

Large-scale scientific simulations require significant resources to generate high-resolution time-varying data (TVD). While super-resolution is an efficient post-processing strategy to reduce costs, existing methods rely on a large amount…

Analytical diffusion models offer a mathematically transparent path to generative modeling by formulating the denoising score as an empirical-Bayes posterior mean. However, this interpretability comes at a prohibitive cost: the standard…

3D reconstruction from a single image is a long-standing problem in computer vision. Learning-based methods address its inherent scale ambiguity by leveraging increasingly large labeled and unlabeled datasets, to produce geometric priors…

Score distillation sampling~(SDS) has been widely adopted to overcome the absence of unseen views in reconstructing 3D objects from a \textbf{single} image. It leverages pre-trained 2D diffusion models as teacher to guide the reconstruction…

We present Diffusion Soup, a compartmentalization method for Text-to-Image Generation that averages the weights of diffusion models trained on sharded data. By construction, our approach enables training-free continual learning and…

Recently, latent diffusion models has demonstrated promising performance in real-world video super-resolution (VSR) task, which can reconstruct high-quality videos from distorted low-resolution input through multiple diffusion steps.…

We propose HYBRIDDEPTH, a robust depth estimation pipeline that addresses key challenges in depth estimation,including scale ambiguity, hardware heterogeneity, and generalizability. HYBRIDDEPTH leverages focal stack, data conveniently…

Training diffusion models is always a computation-intensive task. In this paper, we introduce a novel speed-up method for diffusion model training, called, which is based on a closer look at time steps. Our key findings are: i) Time steps…

Majority of the perception methods in robotics require depth information provided by RGB-D cameras. However, standard 3D sensors fail to capture depth of transparent objects due to refraction and absorption of light. In this paper, we…

Diffusion generative models have achieved remarkable success in generating images with a fixed resolution. However, existing models have limited ability to generalize to different resolutions when training data at those resolutions are not…

Manipulating transparent objects presents significant challenges due to the complexities introduced by their reflection and refraction properties, which considerably hinder the accurate estimation of their 3D shapes. To address these…

Single image 3D reconstruction is an important but challenging task that requires extensive knowledge of our natural world. Many existing methods solve this problem by optimizing a neural radiance field under the guidance of 2D diffusion…

Video Frame Interpolation (VFI) remains a cornerstone in video enhancement, enabling temporal upscaling for tasks like slow-motion rendering, frame rate conversion, and video restoration. While classical methods rely on optical flow and…

We present a method for detecting objects in images using a single deep neural network. Our approach, named SSD, discretizes the output space of bounding boxes into a set of default boxes over different aspect ratios and scales per feature…