Reconstructing and editing 3D objects and scenes both play crucial roles in computer graphics and computer vision. Neural radiance fields (NeRFs) can achieve realistic reconstruction and editing results but suffer from inefficiency in rendering. Gaussian splatting significantly accelerates rendering by rasterizing Gaussian ellipsoids. However, Gaussian splatting utilizes a single Spherical Harmonic (SH) function to model both texture and lighting, limiting independent editing capabilities of these components. Recently, attempts have been made to decouple texture and lighting with the Gaussian splatting representation but may fail to produce plausible geometry and decomposition results on reflective scenes. Additionally, the forward shading technique they employ introduces noticeable blending artifacts during relighting, as the geometry attributes of Gaussians are optimized under the original illumination and may not be suitable for novel lighting conditions. To address these issues, we introduce DeferredGS, a method for decoupling and editing the Gaussian splatting representation using deferred shading. To achieve successful decoupling, we model the illumination with a learnable environment map and define additional attributes such as texture parameters and normal direction on Gaussians, where the normal is distilled from a jointly trained signed distance function. More importantly, we apply deferred shading, resulting in more realistic relighting effects compared to previous methods. Both qualitative and quantitative experiments demonstrate the superior performance of DeferredGS in novel view synthesis and editing tasks.
Path planning is an important problem with the the applications in many aspects, such as video games, robotics etc. This paper proposes a novel method to address the problem of Deep Reinforcement Learning (DRL) based path planning for a mobile robot. We design DRL-based algorithms, including reward functions, and parameter optimization, to avoid time-consuming work in a 2D environment. We also designed an Two-way search hybrid A* algorithm to improve the quality of local path planning. We transferred the designed algorithm to a simple embedded environment to test the computational load of the algorithm when running on a mobile robot. Experiments show that when deployed on a robot platform, the DRL-based algorithm in this article can achieve better planning results and consume less computing resources.
Generating high-quality 3D assets from a given image is highly desirable in various applications such as AR/VR. Recent advances in single-image 3D generation explore feed-forward models that learn to infer the 3D model of an object without optimization. Though promising results have been achieved in single object generation, these methods often struggle to model complex 3D assets that inherently contain multiple objects. In this work, we present ComboVerse, a 3D generation framework that produces high-quality 3D assets with complex compositions by learning to combine multiple models. 1) We first perform an in-depth analysis of this ``multi-object gap'' from both model and data perspectives. 2) Next, with reconstructed 3D models of different objects, we seek to adjust their sizes, rotation angles, and locations to create a 3D asset that matches the given image. 3) To automate this process, we apply spatially-aware score distillation sampling (SSDS) from pretrained diffusion models to guide the positioning of objects. Our proposed framework emphasizes spatial alignment of objects, compared with standard score distillation sampling, and thus achieves more accurate results. Extensive experiments validate ComboVerse achieves clear improvements over existing methods in generating compositional 3D assets.
The emergence of 3D Gaussian Splatting (3DGS) has greatly accelerated the rendering speed of novel view synthesis. Unlike neural implicit representations like Neural Radiance Fields (NeRF) that represent a 3D scene with position and viewpoint-conditioned neural networks, 3D Gaussian Splatting utilizes a set of Gaussian ellipsoids to model the scene so that efficient rendering can be accomplished by rasterizing Gaussian ellipsoids into images. Apart from the fast rendering speed, the explicit representation of 3D Gaussian Splatting facilitates editing tasks like dynamic reconstruction, geometry editing, and physical simulation. Considering the rapid change and growing number of works in this field, we present a literature review of recent 3D Gaussian Splatting methods, which can be roughly classified into 3D reconstruction, 3D editing, and other downstream applications by functionality. Traditional point-based rendering methods and the rendering formulation of 3D Gaussian Splatting are also illustrated for a better understanding of this technique. This survey aims to help beginners get into this field quickly and provide experienced researchers with a comprehensive overview, which can stimulate the future development of the 3D Gaussian Splatting representation.
We present a two-stage text-to-3D generation system, namely 3DTopia, which generates high-quality general 3D assets within 5 minutes using hybrid diffusion priors. The first stage samples from a 3D diffusion prior directly learned from 3D data. Specifically, it is powered by a text-conditioned tri-plane latent diffusion model, which quickly generates coarse 3D samples for fast prototyping. The second stage utilizes 2D diffusion priors to further refine the texture of coarse 3D models from the first stage. The refinement consists of both latent and pixel space optimization for high-quality texture generation. To facilitate the training of the proposed system, we clean and caption the largest open-source 3D dataset, Objaverse, by combining the power of vision language models and large language models. Experiment results are reported qualitatively and quantitatively to show the performance of the proposed system. Our codes and models are available at https://github.com/3DTopia/3DTopia
This research presents a novel depth estimation algorithm based on a Transformer-encoder architecture, tailored for the NYU and KITTI Depth Dataset. This research adopts a transformer model, initially renowned for its success in natural language processing, to capture intricate spatial relationships in visual data for depth estimation tasks. A significant innovation of the research is the integration of a composite loss function that combines Structural Similarity Index Measure (SSIM) with Mean Squared Error (MSE). This combined loss function is designed to ensure the structural integrity of the predicted depth maps relative to the original images (via SSIM) while minimizing pixel-wise estimation errors (via MSE). This research approach addresses the challenges of over-smoothing often seen in MSE-based losses and enhances the model's ability to predict depth maps that are not only accurate but also maintain structural coherence with the input images. Through rigorous training and evaluation using the NYU Depth Dataset, the model demonstrates superior performance, marking a significant advancement in single-image depth estimation, particularly in complex indoor and traffic environments.
Knowledge distillation (KD) has been widely adopted to compress large language models (LLMs). Existing KD methods investigate various divergence measures including the Kullback-Leibler (KL), reverse Kullback-Leibler (RKL), and Jensen-Shannon (JS) divergences. However, due to limitations inherent in their assumptions and definitions, these measures fail to deliver effective supervision when few distribution overlap exists between the teacher and the student. In this paper, we show that the aforementioned KL, RKL, and JS divergences respectively suffer from issues of mode-averaging, mode-collapsing, and mode-underestimation, which deteriorates logits-based KD for diverse NLP tasks. We propose the Sinkhorn Knowledge Distillation (SinKD) that exploits the Sinkhorn distance to ensure a nuanced and precise assessment of the disparity between teacher and student distributions. Besides, profit by properties of the Sinkhorn metric, we can get rid of sample-wise KD that restricts the perception of divergence in each teacher-student sample pair. Instead, we propose a batch-wise reformulation to capture geometric intricacies of distributions across samples in the high-dimensional space. Comprehensive evaluation on GLUE and SuperGLUE, in terms of comparability, validity, and generalizability, highlights our superiority over state-of-the-art methods on all kinds of LLMs with encoder-only, encoder-decoder, and decoder-only architectures.
Manipulating deformable objects is a ubiquitous task in household environments, demanding adequate representation and accurate dynamics prediction due to the objects' infinite degrees of freedom. This work proposes DeformNet, which utilizes latent space modeling with a learned 3D representation model to tackle these challenges effectively. The proposed representation model combines a PointNet encoder and a conditional neural radiance field (NeRF), facilitating a thorough acquisition of object deformations and variations in lighting conditions. To model the complex dynamics, we employ a recurrent state-space model (RSSM) that accurately predicts the transformation of the latent representation over time. Extensive simulation experiments with diverse objectives demonstrate the generalization capabilities of DeformNet for various deformable object manipulation tasks, even in the presence of previously unseen goals. Finally, we deploy DeformNet on an actual UR5 robotic arm to demonstrate its capability in real-world scenarios.
Intelligent robot is the ultimate goal in the robotics field. Existing works leverage learning-based or optimization-based methods to accomplish human-defined tasks. However, the challenge of enabling robots to explore various environments autonomously remains unresolved. In this work, we propose a framework named GExp, which enables robots to explore and learn autonomously without human intervention. To achieve this goal, we devise modules including self-exploration, knowledge-base-building, and close-loop feedback based on foundation models. Inspired by the way that infants interact with the world, GExp encourages robots to understand and explore the environment with a series of self-generated tasks. During the process of exploration, the robot will acquire skills from beneficial experiences that are useful in the future. GExp provides robots with the ability to solve complex tasks through self-exploration. GExp work is independent of prior interactive knowledge and human intervention, allowing it to adapt directly to different scenarios, unlike previous studies that provided in-context examples as few-shot learning. In addition, we propose a workflow of deploying the real-world robot system with self-learned skills as an embodied assistant.
Despite recent advances in text-to-3D generative methods, there is a notable absence of reliable evaluation metrics. Existing metrics usually focus on a single criterion each, such as how well the asset aligned with the input text. These metrics lack the flexibility to generalize to different evaluation criteria and might not align well with human preferences. Conducting user preference studies is an alternative that offers both adaptability and human-aligned results. User studies, however, can be very expensive to scale. This paper presents an automatic, versatile, and human-aligned evaluation metric for text-to-3D generative models. To this end, we first develop a prompt generator using GPT-4V to generate evaluating prompts, which serve as input to compare text-to-3D models. We further design a method instructing GPT-4V to compare two 3D assets according to user-defined criteria. Finally, we use these pairwise comparison results to assign these models Elo ratings. Experimental results suggest our metric strongly align with human preference across different evaluation criteria.