Atlas3D: Physically Constrained Self-Supporting Text-to-3D for Simulation and Fabrication
- URL: http://arxiv.org/abs/2405.18515v2
- Date: Sat, 16 Nov 2024 02:54:28 GMT
- Title: Atlas3D: Physically Constrained Self-Supporting Text-to-3D for Simulation and Fabrication
- Authors: Yunuo Chen, Tianyi Xie, Zeshun Zong, Xuan Li, Feng Gao, Yin Yang, Ying Nian Wu, Chenfanfu Jiang,
- Abstract summary: We introduce Atlas3D, an automatic and easy-to-implement text-to-3D method.
Our approach combines a novel differentiable simulation-based loss function with physically inspired regularization.
We verify Atlas3D's efficacy through extensive generation tasks and validate the resulting 3D models in both simulated and real-world environments.
- Score: 50.541882834405946
- License:
- Abstract: Existing diffusion-based text-to-3D generation methods primarily focus on producing visually realistic shapes and appearances, often neglecting the physical constraints necessary for downstream tasks. Generated models frequently fail to maintain balance when placed in physics-based simulations or 3D printed. This balance is crucial for satisfying user design intentions in interactive gaming, embodied AI, and robotics, where stable models are needed for reliable interaction. Additionally, stable models ensure that 3D-printed objects, such as figurines for home decoration, can stand on their own without requiring additional supports. To fill this gap, we introduce Atlas3D, an automatic and easy-to-implement method that enhances existing Score Distillation Sampling (SDS)-based text-to-3D tools. Atlas3D ensures the generation of self-supporting 3D models that adhere to physical laws of stability under gravity, contact, and friction. Our approach combines a novel differentiable simulation-based loss function with physically inspired regularization, serving as either a refinement or a post-processing module for existing frameworks. We verify Atlas3D's efficacy through extensive generation tasks and validate the resulting 3D models in both simulated and real-world environments.
Related papers
- MagicArticulate: Make Your 3D Models Articulation-Ready [109.35703811628045]
We present MagicArticulate, an effective framework that automatically transforms static 3D models into articulation-ready assets.
Our key contributions are threefold. First, we introduce Articulation-averse benchmark containing over 33k 3D models with high-quality articulation annotations, carefully curated from XL-XL.
Extensive experiments demonstrate that MagicArticulate significantly outperforms existing methods across diverse object categories.
arXiv Detail & Related papers (2025-02-17T18:53:27Z) - TripoSG: High-Fidelity 3D Shape Synthesis using Large-Scale Rectified Flow Models [69.0220314849478]
TripoSG is a new paradigm capable of generating high-fidelity 3D meshes with precise correspondence to input images.
The resulting 3D shapes exhibit en- hanced detail due to high-resolution capabilities and demonstrate exceptional fidelity to input im- ages.
To foster progress and innovation in the field of 3D generation, we will make our model publicly available.
arXiv Detail & Related papers (2025-02-10T16:07:54Z) - GraphicsDreamer: Image to 3D Generation with Physical Consistency [32.26851174969898]
We introduce GraphicsDreamer, a method for creating highly usable 3D meshes from single images.
In the geometry fusion stage, we continue to enforce the PBR constraints, ensuring that the generated 3D objects possess reliable texture details.
Our method incorporates topology optimization and fast UV unwrapping capabilities, allowing the 3D products to be seamlessly imported into graphics engines.
arXiv Detail & Related papers (2024-12-18T10:01:27Z) - GEAL: Generalizable 3D Affordance Learning with Cross-Modal Consistency [50.11520458252128]
Existing 3D affordance learning methods struggle with generalization and robustness due to limited annotated data.
We propose GEAL, a novel framework designed to enhance the generalization and robustness of 3D affordance learning by leveraging large-scale pre-trained 2D models.
GEAL consistently outperforms existing methods across seen and novel object categories, as well as corrupted data.
arXiv Detail & Related papers (2024-12-12T17:59:03Z) - Text-to-3D Gaussian Splatting with Physics-Grounded Motion Generation [47.6666060652434]
We present an innovative framework that generates 3D models with accurate appearances and geometric structures.
By integrating text-to-3D generation with physics-grounded motion synthesis, our framework renders photo-realistic 3D objects.
arXiv Detail & Related papers (2024-12-07T06:48:16Z) - PhysPart: Physically Plausible Part Completion for Interactable Objects [28.91080122885566]
We tackle the problem of physically plausible part completion for interactable objects.
We propose a diffusion-based part generation model that utilizes geometric conditioning.
We also demonstrate our applications in 3D printing, robot manipulation, and sequential part generation.
arXiv Detail & Related papers (2024-08-25T04:56:09Z) - En3D: An Enhanced Generative Model for Sculpting 3D Humans from 2D
Synthetic Data [36.51674664590734]
We present En3D, an enhanced izable scheme for high-qualityd 3D human avatars.
Unlike previous works that rely on scarce 3D datasets or limited 2D collections with imbalance viewing angles and pose priors, our approach aims to develop a zero-shot 3D capable of producing 3D humans.
arXiv Detail & Related papers (2024-01-02T12:06:31Z) - FILP-3D: Enhancing 3D Few-shot Class-incremental Learning with Pre-trained Vision-Language Models [59.13757801286343]
Few-shot class-incremental learning aims to mitigate the catastrophic forgetting issue when a model is incrementally trained on limited data.
We introduce the FILP-3D framework with two novel components: the Redundant Feature Eliminator (RFE) for feature space misalignment and the Spatial Noise Compensator (SNC) for significant noise.
arXiv Detail & Related papers (2023-12-28T14:52:07Z) - AutoDecoding Latent 3D Diffusion Models [95.7279510847827]
We present a novel approach to the generation of static and articulated 3D assets that has a 3D autodecoder at its core.
The 3D autodecoder framework embeds properties learned from the target dataset in the latent space.
We then identify the appropriate intermediate volumetric latent space, and introduce robust normalization and de-normalization operations.
arXiv Detail & Related papers (2023-07-07T17:59:14Z) - Amodal 3D Reconstruction for Robotic Manipulation via Stability and
Connectivity [3.359622001455893]
Learning-based 3D object reconstruction enables single- or few-shot estimation of 3D object models.
Existing 3D reconstruction techniques optimize for visual reconstruction fidelity, typically measured by chamfer distance or voxel IOU.
We propose ARM, an amodal 3D reconstruction system that introduces a stability prior over object shapes, (2) a connectivity prior, and (3) a multi-channel input representation.
arXiv Detail & Related papers (2020-09-28T08:52:54Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.