arXiv subjects

Sheng Ye

Publications and source records attributed to Sheng Ye.

14 recordsLinked to original sources

arXiv2026

SemGS: Feed-Forward Semantic 3D Gaussian Splatting from Sparse Views for Generalizable Scene Understanding

Semantic understanding of 3D scenes is essential for robots to operate effectively and safely in complex environments. Existing methods for semantic scene reconstruction and semantic-aware novel view synthesis often rely on dense multi-view inputs and require scene-specific optimization, limiting their practicality and scalability in real-world applications. To address these challenges, we propose SemGS, a feed-forward framework for reconstructing generalizable semantic fields from sparse image inputs. SemGS uses a dual-branch architecture to extract color and semantic features, where the two branches share shallow CNN layers, allowing semantic reasoning to leverage textural and structural cues in color appearance. We also incorporate a camera-aware attention mechanism into the feature extractor to explicitly model geometric relationships between camera viewpoints. The extracted features are decoded into dual-Gaussians that share geometric consistency while preserving branch-specific attributes, and further rasterized to synthesize semantic maps under novel viewpoints. Additionally, we introduce a regional smoothness loss to enhance semantic coherence. Experiments show that SemGS achieves state-of-the-art performance on benchmark datasets, while providing rapid inference and strong generalization capabilities across diverse synthetic and real-world scenarios.

cs.CV↗

arXiv2025

SCAIL: Towards Studio-Grade Character Animation via In-Context Learning of 3D-Consistent Pose Representations

Achieving controllable character animation that meets studio-grade standards remains challenging despite recent progress. Existing approaches can transfer motion from a driving video to a reference image, but often fail to preserve structural fidelity and temporal consistency in wild scenarios involving complex motion and cross-identity animations. In this work, we present \textbf{SCAIL} (a framework toward \textbf{S}tudio-grade \textbf{C}haracter \textbf{A}nimation via \textbf{I}n-context \textbf{L}earning), which is designed to address these challenges from two key innovations. First, we propose a novel 3D pose representation, providing a robust and flexible motion signal. Second, we introduce a full-context pose injection mechanism within a diffusion-transformer, enabling effective spatio-temporal reasoning over full motion sequences. To align with studio-grade requirements, we develop a curated data pipeline ensuring both diversity and quality, and establish a comprehensive benchmark for systematic evaluation. Experiments show that \textbf{SCAIL} achieves state-of-the-art performance and advances character animation toward studio-grade controlling. Code and model are available at \href{https://github.com/zai-org/SCAIL}{zai-org/SCAIL}.

cs.CV↗

arXiv2025

Response time of electrons to light in strong-field ionization of polar molecules

We study tunneling ionization of HeH+ in strong elliptical laser fields numerically and analytically. The calculated photoelectron momentum distribution (PMD) show two different offset angles corresponding to ionization events occurring in the first and the second half cycles of one laser cycle. When the larger angle is greater than the angle of a model symmetric molecule with a similar ionization potential to the polar molecule, the smaller angle is smaller than the symmetric molecule. Using a developed strong-field model that consider effects of both the permanent dipole (PD) and the asymmetric Coulomb potential, we are able to quantitatively reproduce these phenomena. We show that the PD effect can increase (decrease) the response time of electrons within polar molecules to light in photoemission, thereby increasing (decreasing) the offset angle related to the first (second) half cycle of a laser cycle. The laser-dressed asymmetric Coulomb potential near the atomic nuclei also plays an important role in the sub-cycle-related response time and offset angle. This model may be useful for quantitatively studying attosecond ionization dynamics of polar molecules in strong laser fields.

physics.atom-ph↗

arXiv2025

Learn the Ropes, Then Trust the Wins: Self-imitation with Progressive Exploration for Agentic Reinforcement Learning

Reinforcement learning (RL) is the dominant paradigm for sharpening strategic tool use capabilities of LLMs on long-horizon, sparsely-rewarded agent tasks, yet it faces a fundamental challenge of exploration-exploitation trade-off. Existing studies stimulate exploration through the lens of policy entropy, but such mechanical entropy maximization is prone to RL instability due to the multi-turn distribution shifting. In this paper, we target the progressive exploration-exploitation balance under the guidance of the agent's own experiences without succumbing to either entropy collapsing or runaway divergence. We propose SPEAR, a self-imitation learning (SIL) recipe for training agentic LLMs. It extends the vanilla SIL, where a replay buffer stores good experience for off-policy update, by gradually steering the policy entropy across stages. Specifically, the proposed curriculum scheduling harmonizes intrinsic reward shaping and self-imitation to 1) expedite exploration via frequent tool interactions at the beginning, and 2) strengthen exploitation of successful tactics upon convergence towards familiarity with the environment. We also combine bag-of-tricks of industrial RL optimizations for a strong baseline Dr.BoT to demonstrate our effectiveness. In ALFWorld and WebShop, SPEAR increases the success rates of GRPO/GiGPO/Dr.BoT by up to 16.1%/5.1%/8.6% and 20.7%/11.8%/13.9%, respectively. In AIME24 and AIME25, SPEAR boosts Dr.BoT by up to 3.8% and 6.1%, respectively. Such gains incur only 10%-25% extra theoretical complexity and negligible runtime overhead in practice, demonstrating the plug-and-play scalability of SPEAR.

cs.LG↗

arXiv2025

Explainable artificial intelligence (XAI) for scaling: An application for deducing hydrologic connectivity at watershed scale

Explainable artificial intelligence (XAI) methods have been applied to interpret deep learning model results. However, applications that integrate XAI with established hydrologic knowledge for process understanding remain limited. Here we show that XAI method, applied at point-scale, could be used for cross-scale aggregation of hydrologic responses, a fundamental question in scaling problems, using hydrologic connectivity as a demonstration. Soil moisture and its movement generated by physically based hydrologic model were used to train a long short-term memory (LSTM) network, whose impacts of inputs were evaluated by XAI methods. Our results suggest that XAI-based classification can effectively identify the differences in the functional roles of various sub-regions at watershed scale. The aggregated XAI results could be considered as an explicit and quantitative indicator of hydrologic connectivity development, offering insights to hydrological organization. This framework could be used to facilitate aggregation of other geophysical responses to advance process understandings.

physics.geo-ph↗

arXiv2025

A Text-to-3D Framework for Joint Generation of CG-Ready Humans and Compatible Garments

Creating detailed 3D human avatars with fitted garments traditionally requires specialized expertise and labor-intensive workflows. While recent advances in generative AI have enabled text-to-3D human and clothing synthesis, existing methods fall short in offering accessible, integrated pipelines for generating CG-ready 3D avatars with physically compatible outfits; here we use the term CG-ready for models following a technical aesthetic common in computer graphics (CG) and adopt standard CG polygonal meshes and strands representations (rather than neural representations like NeRF and 3DGS) that can be directly integrated into conventional CG pipelines and support downstream tasks such as physical simulation. To bridge this gap, we introduce Tailor, an integrated text-to-3D framework that generates high-fidelity, customizable 3D avatars dressed in simulation-ready garments. Tailor consists of three stages. (1) Seman tic Parsing: we employ a large language model to interpret textual descriptions and translate them into parameterized human avatars and semantically matched garment templates. (2) Geometry-Aware Garment Generation: we propose topology-preserving deformation with novel geometric losses to generate body-aligned garments under text control. (3) Consistent Texture Synthesis: we propose a novel multi-view diffusion process optimized for garment texturing, which enforces view consistency, preserves photorealistic details, and optionally supports symmetric texture generation common in garments. Through comprehensive quantitative and qualitative evaluations, we demonstrate that Tailor outperforms state-of-the-art methods in fidelity, usability, and diversity. Our code will be released for academic use. Project page: https://human-tailor.github.io

cs.CV↗

arXiv2025

Towards Better Robustness: Pose-Free 3D Gaussian Splatting for Arbitrarily Long Videos

3D Gaussian Splatting (3DGS) has emerged as a powerful representation due to its efficiency and high-fidelity rendering. 3DGS training requires a known camera pose for each input view, typically obtained by Structure-from-Motion (SfM) pipelines. Pioneering works have attempted to relax this restriction but still face difficulties when handling long sequences with complex camera trajectories. In this paper, we propose Rob-GS, a robust framework to progressively estimate camera poses and optimize 3DGS for arbitrarily long video inputs. In particular, by leveraging the inherent continuity of videos, we design an adjacent pose tracking method to ensure stable pose estimation between consecutive frames. To handle arbitrarily long inputs, we propose a Gaussian visibility retention check strategy to adaptively split the video sequence into several segments and optimize them separately. Extensive experiments on Tanks and Temples, ScanNet, and a self-captured dataset show that Rob-GS outperforms the state-of-the-arts.

cs.CV↗

arXiv2024

PVP-Recon: Progressive View Planning via Warping Consistency for Sparse-View Surface Reconstruction

Neural implicit representations have revolutionized dense multi-view surface reconstruction, yet their performance significantly diminishes with sparse input views. A few pioneering works have sought to tackle the challenge of sparse-view reconstruction by leveraging additional geometric priors or multi-scene generalizability. However, they are still hindered by the imperfect choice of input views, using images under empirically determined viewpoints to provide considerable overlap. We propose PVP-Recon, a novel and effective sparse-view surface reconstruction method that progressively plans the next best views to form an optimal set of sparse viewpoints for image capturing. PVP-Recon starts initial surface reconstruction with as few as 3 views and progressively adds new views which are determined based on a novel warping score that reflects the information gain of each newly added view. This progressive view planning progress is interleaved with a neural SDF-based reconstruction module that utilizes multi-resolution hash features, enhanced by a progressive training scheme and a directional Hessian loss. Quantitative and qualitative experiments on three benchmark datasets show that our framework achieves high-quality reconstruction with a constrained input budget and outperforms existing baselines.

cs.CV↗

arXiv2024

Gaussian in the Dark: Real-Time View Synthesis From Inconsistent Dark Images Using Gaussian Splatting

3D Gaussian Splatting has recently emerged as a powerful representation that can synthesize remarkable novel views using consistent multi-view images as input. However, we notice that images captured in dark environments where the scenes are not fully illuminated can exhibit considerable brightness variations and multi-view inconsistency, which poses great challenges to 3D Gaussian Splatting and severely degrades its performance. To tackle this problem, we propose Gaussian-DK. Observing that inconsistencies are mainly caused by camera imaging, we represent a consistent radiance field of the physical world using a set of anisotropic 3D Gaussians, and design a camera response module to compensate for multi-view inconsistencies. We also introduce a step-based gradient scaling strategy to constrain Gaussians near the camera, which turn out to be floaters, from splitting and cloning. Experiments on our proposed benchmark dataset demonstrate that Gaussian-DK produces high-quality renderings without ghosting and floater artifacts and significantly outperforms existing methods. Furthermore, we can also synthesize light-up images by controlling exposure levels that clearly show details in shadow areas.

cs.CV↗

arXiv2023

DiffPoseTalk: Speech-Driven Stylistic 3D Facial Animation and Head Pose Generation via Diffusion Models

The generation of stylistic 3D facial animations driven by speech presents a significant challenge as it requires learning a many-to-many mapping between speech, style, and the corresponding natural facial motion. However, existing methods either employ a deterministic model for speech-to-motion mapping or encode the style using a one-hot encoding scheme. Notably, the one-hot encoding approach fails to capture the complexity of the style and thus limits generalization ability. In this paper, we propose DiffPoseTalk, a generative framework based on the diffusion model combined with a style encoder that extracts style embeddings from short reference videos. During inference, we employ classifier-free guidance to guide the generation process based on the speech and style. In particular, our style includes the generation of head poses, thereby enhancing user perception. Additionally, we address the shortage of scanned 3D talking face data by training our model on reconstructed 3DMM parameters from a high-quality, in-the-wild audio-visual dataset. Extensive experiments and user study demonstrate that our approach outperforms state-of-the-art methods. The code and dataset are at https://diffposetalk.github.io .

cs.CV↗

arXiv2023

Indoor Scene Reconstruction with Fine-Grained Details Using Hybrid Representation and Normal Prior Enhancement

The reconstruction of indoor scenes from multi-view RGB images is challenging due to the coexistence of flat and texture-less regions alongside delicate and fine-grained regions. Recent methods leverage neural radiance fields aided by predicted surface normal priors to recover the scene geometry. These methods excel in producing complete and smooth results for floor and wall areas. However, they struggle to capture complex surfaces with high-frequency structures due to the inadequate neural representation and the inaccurately predicted normal priors. This work aims to reconstruct high-fidelity surfaces with fine-grained details by addressing the above limitations. To improve the capacity of the implicit representation, we propose a hybrid architecture to represent low-frequency and high-frequency regions separately. To enhance the normal priors, we introduce a simple yet effective image sharpening and denoising technique, coupled with a network that estimates the pixel-wise uncertainty of the predicted surface normal vectors. Identifying such uncertainty can prevent our model from being misled by unreliable surface normal supervisions that hinder the accurate reconstruction of intricate geometries. Experiments on the benchmark datasets show that our method outperforms existing methods in terms of reconstruction quality. Furthermore, the proposed method also generalizes well to real-world indoor scenarios captured by our hand-held mobile phones. Our code is publicly available at: https://github.com/yec22/Fine-Grained-Indoor-Recon.

cs.CV↗

arXiv2023

O$^2$-Recon: Completing 3D Reconstruction of Occluded Objects in the Scene with a Pre-trained 2D Diffusion Model

Occlusion is a common issue in 3D reconstruction from RGB-D videos, often blocking the complete reconstruction of objects and presenting an ongoing problem. In this paper, we propose a novel framework, empowered by a 2D diffusion-based in-painting model, to reconstruct complete surfaces for the hidden parts of objects. Specifically, we utilize a pre-trained diffusion model to fill in the hidden areas of 2D images. Then we use these in-painted images to optimize a neural implicit surface representation for each instance for 3D reconstruction. Since creating the in-painting masks needed for this process is tricky, we adopt a human-in-the-loop strategy that involves very little human engagement to generate high-quality masks. Moreover, some parts of objects can be totally hidden because the videos are usually shot from limited perspectives. To ensure recovering these invisible areas, we develop a cascaded network architecture for predicting signed distance field, making use of different frequency bands of positional encoding and maintaining overall smoothness. Besides the commonly used rendering loss, Eikonal loss, and silhouette loss, we adopt a CLIP-based semantic consistency loss to guide the surface from unseen camera angles. Experiments on ScanNet scenes show that our proposed framework achieves state-of-the-art accuracy and completeness in object-level reconstruction from scene-level RGB-D videos. Code: https://github.com/THU-LYJ-Lab/O2-Recon.

cs.CV↗

arXiv2021

Towards GaAs Thin-Film Tracking Detectors

Silicon-based tracking detectors have been used in several important applications, such as in cancer therapy using particle beams, and for the discovery of new elementary particles at the Large Hadron Collider at CERN. III-V semiconductor materials are an attractive alternative to silicon for this application, as they have some superior physical properties. They could meet the demands for fast timing detectors allowing time-of-flight measurements with ps resolution while being radiation tolerant and cost-efficient. As a material with a larger density, higher atomic number Z and much higher electron mobility than silicon, GaAs exhibits faster signal collection and a larger signal per {\mu}m of sensor thickness. In this work, we report on the fabrication of n-in-n GaAs thin-film devices intended to serve next-generation high-energy particle tracking detectors. Molecular beam epitaxy (MBE) was used to grow high-quality GaAs films with doping levels sufficiently low to achieve full depletion for detectors with an active thickness of 10 {\mu}m. The signal collection speed of the detector structures was assessed using the transient current technique (TCT). To elucidate the structural properties of the detector, Kelvin probe force microscopy (KPFM) was used, which confirmed the formation of the junction in the detector and revealed residual doping in the intrinsic layer. Our results suggest that GaAs thin films are suitable candidates to achieve thin and radiation-tolerant tracking detectors.

physics.ins-det↗

arXiv2020

Efficient and Accurate Simulations of Vibrational and Electronic Spectra with Symmetry-Preserving Neural Network Models for Tensorial Properties

Machine learning has revolutionized the high-dimensional representations for molecular properties such as potential energy. However, there are scarce machine learning models targeting tensorial properties, which are rotationally covariant. Here, we propose tensorial neural network (NN) models to learn both tensorial response and transition properties, in which atomic coordinate vectors are multiplied with scalar NN outputs or their derivatives to preserve the rotationally covariant symmetry. This strategy keeps structural descriptors symmetry invariant so that the resulting tensorial NN models are as efficient as their scalar counterparts. We validate the performance and universality of this approach by learning response properties of water oligomers and liquid water, and transition dipole moment of a model structural unit of proteins. Machine learned tensorial models have enabled efficient simulations of vibrational spectra of liquid water and ultraviolet spectra of realistic proteins, promising feasible and accurate spectroscopic simulations for biomolecules and materials.

physics.chem-ph↗