Related papers: SceneForge: Structured World Supervision from 3D I…
Scene text erasing seeks to erase text contents from scene images and current state-of-the-art text erasing models are trained on large-scale synthetic data. Although data synthetic engines can provide vast amounts of annotated training…
We propose a method for editing NeRF scenes with text-instructions. Given a NeRF of a scene and the collection of images used to reconstruct it, our method uses an image-conditioned diffusion model (InstructPix2Pix) to iteratively edit the…
Scene text editing seeks to modify textual content in natural images while maintaining visual realism and semantic consistency. Existing methods often require task-specific training or paired data, limiting their scalability and…
Empowering models to dynamically accomplish tasks specified through natural language instructions represents a promising path toward more capable and general artificial intelligence. In this work, we introduce InstructSeq, an…
Continual learning refers to the ability of humans and animals to incrementally learn over time in a given environment. Trying to simulate this learning process in machines is a challenging task, also due to the inherent difficulty in…
Advances in computer networks and rendering systems facilitate the creation of distributed collaborative environments in which the distribution of information at remote locations allows efficient communication. One of the challenges in…
Unbounded 3D world generation is emerging as a foundational task for scene modeling in computer vision, graphics, and robotics. In this work, we present WorldFlow3D, a novel method capable of generating unbounded 3D worlds. Building upon a…
Existing methods for the 4D reconstruction of general, non-rigidly deforming objects focus on novel-view synthesis and neglect correspondences. However, time consistency enables advanced downstream tasks like 3D editing, motion analysis, or…
Image fusion is a technique to integrate information from multiple source images with complementary information to improve the richness of a single image. Due to insufficient task-specific training data and corresponding ground truth, most…
In the field of 3D content generation, single image scene reconstruction methods still struggle to simultaneously ensure the quality of individual assets and the coherence of the overall scene in complex environments, while texture editing…
This paper introduces innovative solutions to enhance spatial controllability in diffusion models reliant on text queries. We first introduce vision guidance as a foundational spatial cue within the perturbed distribution. This…
The existing deep learning fusion methods mainly concentrate on the convolutional neural networks, and few attempts are made with transformer. Meanwhile, the convolutional operation is a content-independent interaction between the image and…
Embodied intelligence requires high-fidelity simulation environments to support perception and decision-making, yet existing platforms often suffer from data contamination and limited flexibility. To mitigate this, we propose…
Scene generation has extensive industrial applications, demanding both high realism and precise control over geometry and appearance. Language-driven retrieval methods compose plausible scenes from a large object database, but overlook…
We introduce InstructVid2Vid, an end-to-end diffusion-based methodology for video editing guided by human language instructions. Our approach empowers video manipulation guided by natural language directives, eliminating the need for…
Recent works on text-to-3d generation show that using only 2D diffusion supervision for 3D generation tends to produce results with inconsistent appearances (e.g., faces on the back view) and inaccurate shapes (e.g., animals with extra…
We investigate the problem of identifying objects that have been added, removed, or moved between a pair of captures (images or videos) of the same scene at different times. Accurately identifying verifiable changes is extremely challenging…
Capturing contextual dependencies has proven useful to improve the representational power of deep neural networks. Recent approaches that focus on modeling global context, such as self-attention and non-local operation, achieve this goal by…
Comprehending natural language instructions is a charming property for 3D indoor scene synthesis systems. Existing methods directly model object joint distributions and express object relations implicitly within a scene, thereby hindering…
Reconstructing dynamic driving scenes from dashcam videos has attracted increasing attention due to its significance in autonomous driving and scene understanding. While recent advances have made impressive progress, most methods still…