Related papers: SegviGen: Repurposing 3D Generative Model for Part…

Training a generalizable 3D part segmentation network is quite challenging but of great importance in real-world applications. To tackle this problem, some works design task-specific solutions by translating human understanding of the task…

Objects often occlude each other in scenes; Inferring their appearance beyond their visible parts plays an important role in scene understanding, depth estimation, object interaction and manipulation. In this paper, we study the challenging…

In recent years, 3D Gaussian splatting has emerged as a powerful technique for 3D reconstruction and generation, known for its fast and high-quality rendering capabilities. To address these shortcomings, this paper introduces a novel…

By pretraining to synthesize coherent images from perturbed inputs, generative models inherently learn to understand object boundaries and scene compositions. How can we repurpose these generative representations for general-purpose…

Modern generative models achieve excellent quality in a variety of tasks including image or text generation and chemical molecule modeling. However, existing methods often lack the essential ability to generate examples with requested…

Segmenting 3D assets into their constituent parts is crucial for enhancing 3D understanding, facilitating model reuse, and supporting various applications such as part generation. However, current methods face limitations such as poor…

This paper proposes a convolutional neural network that can fuse high-level prior for semantic image segmentation. Motivated by humans' vision recognition system, our key design is a three-layer generative structure consisting of high-level…

We present a deep learning pipeline that leverages network self-prior to recover a full 3D model consisting of both a triangular mesh and a texture map from the colored 3D point cloud. Different from previous methods either exploiting 2D…

Driven by powerful image diffusion models, recent research has achieved the automatic creation of 3D objects from textual or visual guidance. By performing score distillation sampling (SDS) iteratively across different views, these methods…

Recent advances in generative models, such as diffusion models, have made generating high-quality synthetic images widely accessible. Prior works have shown that training on synthetic images improves many perception tasks, such as image…

In this paper, we present InSeGAN, an unsupervised 3D generative adversarial network (GAN) for segmenting (nearly) identical instances of rigid objects in depth images. Using an analysis-by-synthesis approach, we design a novel GAN…

We present a novel and practical deep fully convolutional neural network architecture for semantic pixel-wise segmentation termed SegNet. This core trainable segmentation engine consists of an encoder network, a corresponding decoder…

While visual autoregressive modeling (VAR) strategies have shed light on image generation with the autoregressive models, their potential for segmentation, a task that requires precise low-level spatial perception, remains unexplored.…

3D generative models have been recently successful in generating realistic 3D objects in the form of point clouds. However, most models do not offer controllability to manipulate the shape semantics of component object parts without…

Given a 3D mesh, we aim to synthesize 3D textures that correspond to arbitrary textual descriptions. Current methods for generating and assembling textures from sampled views often result in prominent seams or excessive smoothing. To tackle…

Generating 3D human motions from textual descriptions is an important research problem with broad applications in video games, virtual reality, and augmented reality. Recent methods align the textual description with human motion at the…

While Multimodal Large Language Models demonstrate impressive semantic capabilities, they often suffer from spatial blindness, struggling with fine-grained geometric reasoning and physical dynamics. Existing solutions typically rely on…

We introduce a new encoder-decoder GAN model, FutureGAN, that predicts future frames of a video sequence conditioned on a sequence of past frames. During training, the networks solely receive the raw pixel values as an input, without…

The problem of segmenting a given image into coherent regions is important in Computer Vision and many industrial applications require segmenting a known object into its components. Examples include identifying individual parts of a…

We introduce a new approach to high-fidelity 3D scene reconstruction from multi-view RGB images that tightly couples reconstruction with a strong generative 3D prior. We cast scene reconstruction as conditional 3D generation over a set of…