Related papers: How to Spin an Object: First, Get the Shape Right
Robust 3D representation learning forms the perceptual foundation of spatial intelligence, enabling downstream tasks in scene understanding and embodied AI. However, learning such representations directly from unposed multi-view images…
For improving image composition and aesthetic quality, most existing methods modulate the captured images by striking out redundant content near the image borders. However, such image cropping methods are limited in the range of image…
The rapid growth of 3D digital content necessitates expandable recognition systems for open-world scenarios. However, existing 3D class-incremental learning methods struggle under extreme data scarcity due to geometric misalignment and…
Commercial off the shelf (COTS) 3D scanners are capable of generating point clouds covering visible portions of a face with sub-millimeter accuracy at close range, but lack the coverage and specialized anatomic registration provided by more…
We present a simple yet effective general-purpose framework for modeling 3D shapes by leveraging recent advances in 2D image generation using CNNs. Using just a single depth image of the object, we can output a dense multi-view depth map…
Dynamic scene reconstruction from casual videos has seen recent remarkable progress. Numerous approaches have attempted to overcome the ill-posedness of the task by distilling priors from 2D foundational models and by imposing hand-crafted…
Encoding 3D points is one of the primary steps in learning-based implicit scene representation. Using features that gather information from neighbors with multi-resolution grids has proven to be the best geometric encoder for this task.…
A major endeavor of computer vision is to represent, understand and extract structure from 3D data. Towards this goal, unsupervised learning is a powerful and necessary tool. Most current unsupervised methods for 3D shape analysis use…
We introduce Duoduo CLIP, a model for 3D representation learning that learns shape encodings from multi-view images instead of point clouds. The choice of multi-view images allows us to leverage 2D priors from off-the-shelf CLIP models to…
The goal of many computer vision systems is to transform image pixels into 3D representations. Recent popular models use neural networks to regress directly from pixels to 3D object parameters. Such an approach works well when supervision…
3D visual grounding allows an embodied agent to understand visual information in real-world 3D environments based on human instructions, which is crucial for embodied intelligence. Existing 3D visual grounding methods typically rely on…
While the proposal of the Tri-plane representation has advanced the development of the 3D-aware image generative models, problems rooted in its inherent structure, such as multi-face artifacts caused by sharing the same features in…
Single-image-to-3D models typically follow a sequential generation and reconstruction workflow. However, intermediate multi-view images synthesized by pre-trained generation models often lack cross-view consistency (CVC), significantly…
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…
Shape priors learned from data are commonly used to reconstruct 3D objects from partial or noisy data. Yet no such shape priors are available for indoor scenes, since typical 3D autoencoders cannot handle their scale, complexity, or…
Despite strong single-turn performance, diffusion-based image compositing often struggles to preserve coherent spatial relations in pairwise or sequential edits, where subsequent insertions may overwrite previously generated content and…
We present a framework for learning 3D object shapes and dense cross-object 3D correspondences from just an unaligned category-specific image collection. The 3D shapes are generated implicitly as deformations to a category-specific signed…
In the area of 3D shape analysis, the geometric properties of a shape have long been studied. Instead of directly extracting representative features using expert-designed descriptors or end-to-end deep neural networks, this paper is…
Recent 3D large reconstruction models typically employ a two-stage process, including first generate multi-view images by a multi-view diffusion model, and then utilize a feed-forward model to reconstruct images to 3D content.However,…
High-confidence overlap prediction and accurate correspondences are critical for cutting-edge models to align paired point clouds in a partial-to-partial manner. However, there inherently exists uncertainty between the overlapping and…