相关论文: MM-3DScene: 3D Scene Understanding by Customizing …

3D scene reconstruction from 2D images has been a long-standing task. Instead of estimating per-frame depth maps and fusing them in 3D, recent research leverages the neural implicit surface as a unified representation for 3D reconstruction.…

Self-supervised learning has transformed 2D computer vision by enabling models trained on large, unannotated datasets to provide versatile off-the-shelf features that perform similarly to models trained with labels. However, in 3D scene…

Masked signal modeling has greatly advanced self-supervised pre-training for language and 2D images. However, it is still not fully explored in 3D scene understanding. Thus, this paper introduces Masked Shape Prediction (MSP), a new…

In this study, we address the challenge of 3D scene structure recovery from monocular depth estimation. While traditional depth estimation methods leverage labeled datasets to directly predict absolute depth, recent advancements advocate…

As a pioneering work, PointContrast conducts unsupervised 3D representation learning via leveraging contrastive learning over raw RGB-D frames and proves its effectiveness on various downstream tasks. However, the trend of large-scale…

Aiming at inferring 3D shapes from 2D images, 3D shape reconstruction has drawn huge attention from researchers in computer vision and deep learning communities. However, it is not practical to assume that 2D input images and their…

Object recognition has seen significant progress in the image domain, with focus primarily on 2D perception. We propose to leverage existing large-scale datasets of 3D models to understand the underlying 3D structure of objects seen in an…

Constructing compact and informative 3D scene representations is essential for effective embodied exploration and reasoning, especially in complex environments over extended periods. Existing representations, such as object-centric 3D scene…

Masked Image Modeling (MIM) achieves outstanding success in self-supervised representation learning. Unfortunately, MIM models typically have huge computational burden and slow learning process, which is an inevitable obstacle for their…

Reasoning segmentation aims to segment target objects in complex scenes based on human intent and spatial reasoning. While recent multimodal large language models (MLLMs) have demonstrated impressive 2D image reasoning segmentation,…

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…

Although Multimodal Large Language Models have achieved remarkable progress, they still struggle with complex 3D spatial reasoning due to the reliance on 2D visual priors. Existing approaches typically mitigate this limitation either…

While deep learning methods have achieved impressive success in many vision benchmarks, it remains difficult to understand and explain the representations and decisions of these models. Though vision models are typically trained on 2D…

The precise reconstruction of 3D objects from a single RGB image in complex scenes presents a critical challenge in virtual reality, autonomous driving, and robotics. Existing neural implicit 3D representation methods face significant…

Masking strategies commonly employed in natural language processing are still underexplored in vision tasks such as concept learning, where conventional methods typically rely on full images. However, using masked images diversifies…

Most deep learning approaches to comprehensive semantic modeling of 3D indoor spaces require costly dense annotations in the 3D domain. In this work, we explore a central 3D scene modeling task, namely, semantic scene reconstruction without…

3D Morphable Model (3DMM) fitting has widely benefited face analysis due to its strong 3D priori. However, previous reconstructed 3D faces suffer from degraded visual verisimilitude due to the loss of fine-grained geometry, which is…

Recent advances in 3D scene-language understanding have leveraged Large Language Models (LLMs) for 3D reasoning by transferring their general reasoning ability to 3D multi-modal contexts. However, existing methods typically adopt standard…

Recent advancements in multi-view 3D reconstruction and novel-view synthesis, particularly through Neural Radiance Fields (NeRF) and 3D Gaussian Splatting (3DGS), have greatly enhanced the fidelity and efficiency of 3D content creation.…

Foundation models have achieved remarkable results in 2D and language tasks like image segmentation, object detection, and visual-language understanding. However, their potential to enrich 3D scene representation learning is largely…