图形学
Synthesizing 3D scenes from open-vocabulary text descriptions is a challenging, important, and recently-popular application. One of its critical subproblems is layout generation: given a set of objects, lay them out to produce a scene…
This paper introduces a method to extract a hierarchical tree representation from 3D unorganized polygonal data. The proposed approach first extracts a graph representation of the surface, which serves as the foundation for structural…
Cities are important elements of content in digital productions, but their complexity and size make them very challenging to model. Few tools exist that can help artists with this work, even as rapid improvements in graphics hardware create…
We propose an adaptive form of frameless rendering with the potential to dramatically increase rendering speed over conventional interactive rendering approaches. Without the rigid sampling patterns of framed renderers, sampling and…
Integrating motion into static images not only enhances visual expressiveness but also creates a sense of immersion and temporal depth, establishing it as a longstanding and impactful theme in artistic expression. Fluid elements such as…
In this paper, we propose a two-stage sketch-based smoke illustration generation framework using stream function and latent diffusion models (LDM). The user sketch is used to guide the generation of the stream function, which serves as the…
In this paper, we formulate the problem of kinematic synthesis for planar linkages as a cross-domain image generation task. We develop a planar linkages dataset using RGB image representations, covering a range of mechanisms: from simple…
Motion retargeting holds a premise of offering a larger set of motion data for characters and robots with different morphologies. Many prior works have approached this problem via either handcrafted constraints or paired motion datasets,…
Opaque objects reconstructed by 3DGS often exhibit a falsely transparent surface, leading to inconsistent background and internal patterns under camera motion in interactive viewing. This issue stems from the ill-posed optimization in 3DGS.…
We tackle the challenge of efficiently reconstructing 3D scenes with high detail on objects of interest. Existing 3D Gaussian Splatting (3DGS) methods allocate resources uniformly across the scene, limiting fine detail to Regions Of…
Processing visual data often involves small adjustments or sequences of changes, e.g., image filtering, surface smoothing, and animation. While established graphics techniques like normal mapping and video compression exploit redundancy to…
Prompt-based models have demonstrated impressive prompt-following capability at image editing tasks. However, the models still struggle with following detailed editing prompts or performing local edits. Specifically, global image quality…
Current methods for generating 3D scene layouts from text predominantly follow a declarative paradigm, where a Large Language Model (LLM) specifies high-level constraints that are then resolved by a separate solver. This paper challenges…
Many network architectures exist for learning on meshes, yet their constructions entail delicate trade-offs between difficulty learning high-frequency features, insufficient receptive field, sensitivity to discretization, and inefficient…
Rendering huge biological scenes with atomistic detail presents a significant challenge in molecular visualization due to the memory limitations inherent in traditional rendering approaches. In this paper, we propose a novel method for the…
Traditional integral wood joints, despite their strength, durability, and elegance, remain rare in modern workflows due to the cost and difficulty of manual fabrication. CNC milling offers a scalable alternative, but directly milling…
Recent talking head synthesis works typically adopt speech features extracted from large-scale pre-trained acoustic models. However, the intrinsic many-to-many relationship between speech and lip motion causes phoneme-viseme alignment…
The deployment of autonomous virtual avatars (in extended reality) and robots in human group activities -- such as rehabilitation therapy, sports, and manufacturing -- is expected to increase as these technologies become more pervasive.…
We propose a parameter optimization method for achieving static equilibrium of discrete elastic rods. Our method simultaneously optimizes material stiffness and rest shape parameters under box constraints to exactly enforce zero net force…
Representation learning on text-attributed graphs (TAGs) integrates structural connectivity with rich textual semantics, enabling applications in diverse domains. Current methods largely rely on contrastive learning to maximize cross-modal…