38 papers
This paper introduces ARSGaussian, a novel view synthesis method for aerial remote sensing that integrates LiDAR constraints, distortion-aware coordinate transformations, and geometric consistency losses to mitigate floaters and overgrowth while achieving high-precision geo-alignment, supported by the newly released AIR-LONGYAN dataset.
This study involving 72 participants across three languages demonstrates that while nominal groups serve as a crucial benchmark for evaluating collaborative virtual environments, 3D graph representations in mixed reality do not inherently yield better collaborative problem-solving outcomes than individual performance.
This paper identifies a structural gradient failure in Chamfer distance optimization that causes point cloud collapse, demonstrating that introducing non-local coupling mechanisms is a necessary condition to suppress this collapse and achieve successful 3D shape optimization.
This paper introduces "CVDLoss," a novel metric for evaluating color accessibility in diffusion-based image generation, and demonstrates that current models struggle to reliably respond to accessibility-focused prompts despite the metric's sensitivity to structural detail changes.
This paper presents a comprehensive study of Time-of-Flight non-line-of-sight imaging methods by unifying their theoretical formulations and hardware implementations to establish a common framework for analysis and demonstrate that, under equal constraints, existing techniques share similar performance limitations despite method-specific differences.
This paper introduces M-ABD, a scalable and robust framework that leverages linear kinematic mapping and a compact dual-space formulation of Affine Body Dynamics to enable interactive, stable simulation of large-scale articulated assemblies with hundreds of thousands of bodies on a single CPU core.
This paper introduces MambaDance, a novel dance generation framework that replaces Transformers with a Mamba-based diffusion model and employs a Gaussian-based beat representation to effectively capture the sequential, rhythmic, and music-synchronized nature of dance across varying sequence lengths.
TeamHOI is a decentralized framework that leverages a Transformer-based policy and a masked Adversarial Motion Prior strategy to enable a single unified policy to control scalable, physically realistic cooperative human-object interactions among any number of humanoid agents.
This paper proposes a novel style transfer method that represents images in the brushstroke domain rather than the traditional pixel domain, offering a more natural and visually superior approach to mimicking artistic styles.
Ref-DGS is an efficient, rasterization-based framework that achieves state-of-the-art novel view synthesis on reflective scenes by decoupling surface geometry from specular reflections using a dual Gaussian representation and a lightweight adaptive mixing shader, thereby avoiding the high computational cost of explicit ray tracing.
FabricGen is an end-to-end framework that generates realistic woven fabric materials from text by decoupling macro-scale texture synthesis via fine-tuned diffusion models from micro-scale weaving pattern generation using a specialized LLM-driven procedural geometric model.
The paper introduces MultiGen, a novel diffusion-based game engine that incorporates an explicit, persistent external memory to enable user-editable world structures and support coherent, real-time multiplayer interactions, overcoming the limitations of conventional next-frame prediction models.
This paper provides a comprehensive technical survey of the history and evolution of image generation models, detailing the objectives, architectures, and limitations of various approaches from VAEs to diffusion methods, while also addressing recent advancements in video generation and the critical challenges of robustness and responsible deployment.
The paper introduces RAF (Retrieval-Augmented Faces), a training-time augmentation method that enhances the expression generalization and robustness of template-free animatable head avatars by dynamically replacing subject features with nearest-neighbor expressions from a large unlabeled bank, thereby improving fidelity in both self-driving and cross-driving scenarios without requiring additional data or architectural changes.
TopGen is a robust, learning-based framework that simultaneously predicts structural layouts and cross-fields to generate high-quality quadrilateral meshes, overcoming the efficiency and topological limitations of traditional methods while preserving geometric integrity and editability.
This paper presents a reproducible comparison of Clough-Tocher and Multiquadric RBF interpolants, demonstrating that while both methods overfit noisy data, the cubic interpolant offers greater stability and that noisy thermodynamic measurements can be effectively structured to recover meaningful process behavior.
This paper proposes LM-4DGAN, a generative model that utilizes neutral landmarks, an identity discriminator, a landmark autoencoder, and a cross-attention mechanism to synthesize robust 4D facial expressions across different identities, addressing the limitations of existing label or speech-guided approaches.
This paper proposes FC-4DFS, a frequency-controlled method utilizing a frequency-controlled LSTM and a Multi-level Identity-Aware Displacement Network with a temporal coherence loss to generate flexible, smooth, and state-of-the-art 4D facial expression sequences of varying lengths from neutral landmarks.
The paper proposes LiTo, a unified 3D latent representation that tokenizes surface light fields from RGB-depth images to jointly model geometry and view-dependent appearance, enabling high-fidelity 3D object generation with realistic lighting effects via a latent flow matching model.
ID-LoRA is a novel framework that unifies audio and video personalization in a single generative pass by adapting the LTX-2 diffusion backbone with identity-driven In-Context LoRA and specialized techniques like negative temporal positions and identity guidance, achieving superior voice and visual likeness with minimal training data.