paper-with-me

홈 › Papers

SplaTraj: Camera Trajectory Generation with Semantic Gaussian Splatting

2024-10-08 · Xinyi Liu, Tianyi Zhang, Matthew Johnson-Roberson, Weiming Zhi

Many recent developments for robots to represent environments have focused on photorealistic reconstructions. This paper particularly focuses on generating sequences of images from the photorealistic Gaussian Splatting models, that match instructions that are given by user-inputted language. We contribute a novel framework, SplaTraj, which formulates the generation of images within photorealistic environment representations as a continuous-time trajectory optimization problem. Costs are designed so that a camera following the trajectory poses will smoothly traverse through the environment and render the specified spatial information in a photogenic manner. This is achieved by querying a photorealistic representation with language embedding to isolate regions that correspond to the user-specified inputs. These regions are then projected to the camera's view as it moves over time and a cost is constructed. We can then apply gradient-based optimization and differentiate through the rendering to optimize the trajectory for the defined cost. The resulting trajectory moves to photogenically view each of the specified objects. We empirically evaluate our approach on a suite of environments and instructions, and demonstrate the quality of generated image sequences.

📄 PDF Abstract BibTeX arXiv:2410.06014

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Director3D: Real-world Camera Trajectory and 3D Scene Generation from Text

2024-06-25 · Xinyang Li, Zhangyu Lai, Linning Xu, Yansong Qu 외

Recent advancements in 3D generation have leveraged synthetic datasets with ground truth 3D assets and predefined cameras. However, the potential of adopting real-world datasets, which can produce significantly more real…

3D GenerationDenoisingScene GenerationText to 3D

Unified Panoramic-Gaussian Representation for Monocular 4D Scene Synthesis

2026-07-02 · Yuankun Yang, Yi Wei, Wenyang Zhou, Li Zhang arxiv

4D scene synthesis from monocular videos has made significant progress in recent years. However, existing methods are typically constrained by view interpolation. As a result, they struggle to infer unseen regions beyond…

Video Generation

HouseTour: A Virtual Real Estate A(I)gent

2025-10-20 · Ata Çelen, Marc Pollefeys, Daniel Barath, Iro Armeni arxiv

We introduce HouseTour, a method for spatially-aware 3D camera trajectory and natural language summary generation from a collection of images depicting an existing 3D space. Unlike existing vision-language models (VLMs),…

Text Generation

Track2Map: Online Deformable SLAM with Motion-Aware Pose Optimization in Robotic Surgery

2026-07-09 · Tianyi Song, Sierra Bonilla, Xinwei Ju, Evangelos Mazomenos 외 arxiv

Gaussian splatting is the current state-of-the-art for dense, deformable 3D anatomy reconstruction in robot-assisted minimally invasive surgery (RAMIS); however, most pipelines are offline and depend on accurate camera t…

MotionFlow:Learning Implicit Motion Flow for Complex Camera Trajectory Control in Video Generation

2025-09-25 · Guojun Lei, Chi Wang, Yikai Wang, Hong Li 외 arxiv

Generating videos guided by camera trajectories poses significant challenges in achieving consistency and generalizability, particularly when both camera and object motions are present. Existing approaches often attempt …

Video Generation