Related papers: FacaDiffy: Inpainting Unseen Facade Parts Using Di…

A major challenge in reconstructing buildings from LiDAR point clouds lies in accurately capturing building surfaces under varying point densities and noise interference. To flexibly gather high-quality 3D profiles of the building in…

Recent advances in generative modeling -- particularly diffusion models and flow matching -- have achieved remarkable success in synthesizing discrete data such as images and videos. However, adapting these models to physical applications…

Face inpainting techniques recover missing or occluded facial regions in a visually realistic manner, but preserving the identity in the final output remains a fundamental challenge. Identity consistency is crucial for downstream…

Denoising diffusion models are a powerful type of generative models used to capture complex distributions of real-world signals. However, their applicability is limited to scenarios where training samples are readily available, which is not…

Scene flow estimation, which aims to predict per-point 3D displacements of dynamic scenes, is a fundamental task in the computer vision field. However, previous works commonly suffer from unreliable correlation caused by locally constrained…

Inpainting focuses on filling missing or corrupted regions of an image to blend seamlessly with its surrounding content and style. While conditional diffusion models have proven effective for text-guided inpainting, we introduce the novel…

We present Surf-D, a novel method for generating high-quality 3D shapes as Surfaces with arbitrary topologies using Diffusion models. Previous methods explored shape generation with different representations and they suffer from limited…

The task of 3D shape captioning occupies a significant place within the domain of computer graphics and has garnered considerable interest in recent years. Traditional approaches to this challenge frequently depend on the utilization of…

As one of the most successful generative models, diffusion models have demonstrated remarkable efficacy in synthesizing high-quality images. These models learn the underlying high-dimensional data distribution in an unsupervised manner.…

Graph diffusion models have gained significant attention in graph generation tasks, but they often inherit and amplify topology biases from sensitive attributes (e.g. gender, age, region), leading to unfair synthetic graphs. Existing fair…

Due to the high potential for abuse of GenAI systems, the task of detecting synthetic images has recently become of great interest to the research community. Unfortunately, existing image-space detectors quickly become obsolete as new…

Predicting human gaze scanpaths is crucial for understanding visual attention, with applications in human-computer interaction, autonomous systems, and cognitive robotics. While deep learning models have advanced scanpath prediction, most…

Probabilistic diffusion models have achieved state-of-the-art results for image synthesis, inpainting, and text-to-image tasks. However, they are still in the early stages of generating complex 3D shapes. This work proposes Diffusion-SDF, a…

Free-form image inpainting is the task of reconstructing parts of an image specified by an arbitrary binary mask. In this task, it is typically desired to generalize model capabilities to unseen mask types, rather than learning certain mask…

We introduce a new diffusion-based approach for shape completion on 3D range scans. Compared with prior deterministic and probabilistic methods, we strike a balance between realism, multi-modality, and high fidelity. We propose DiffComplete…

Current 3D inpainting and object removal methods are largely limited to front-facing scenes, facing substantial challenges when applied to diverse, "unconstrained" scenes where the camera orientation and trajectory are unrestricted. To…

We present SemLayoutDiff, a unified model for synthesizing diverse 3D indoor scenes across multiple room types. The model introduces a scene layout representation combining a top-down semantic map and attributes for each object. Unlike…

Diffusion models have emerged as a leading technique for generating images due to their ability to create high-resolution and realistic images. Despite their strong performance, diffusion models still struggle in managing image collections…

Differentiable rendering is an essential operation in modern vision, allowing inverse graphics approaches to 3D understanding to be utilized in modern machine learning frameworks. Explicit shape representations (voxels, point clouds, or…

Generating unbounded 3D scenes is crucial for large-scale scene understanding and simulation. Urban scenes, unlike natural landscapes, consist of various complex man-made objects and structures such as roads, traffic signs, vehicles, and…