Related papers: Forest2Seq: Revitalizing Order Prior for Sequentia…

Learning-based methods for 3D scene reconstruction and object completion require large datasets containing partial scans paired with complete ground-truth geometry. However, acquiring such datasets using real-world scanning systems is…

Generalization remains the central challenge for interactive 3D scene generation. Existing learning-based approaches ground spatial understanding in limited scene dataset, restricting generalization to new layouts. We instead reprogram a…

We live in a 3D world, performing activities and interacting with objects in the indoor environments everyday. Indoor scenes are the most familiar and essential environments in everyone's life. In the virtual world, 3D indoor scenes are…

As two intimate reciprocal tasks, scene-aware human motion synthesis and analysis require a joint understanding between multiple modalities, including 3D body motions, 3D scenes, and textual descriptions. In this paper, we integrate these…

Sketching is inherently a sequential process, in which strokes are drawn in a meaningful order to explore and refine ideas. However, most generative models treat sketches as static images, overlooking the temporal structure that underlies…

We introduce Infinigen Indoors, a Blender-based procedural generator of photorealistic indoor scenes. It builds upon the existing Infinigen system, which focuses on natural scenes, but expands its coverage to indoor scenes by introducing a…

We tackle the challenge of generating the infinitely extendable 3D world -- large, continuous environments with coherent geometry and realistic appearance. Existing methods face key challenges: 2D-lifting approaches suffer from geometric…

We introduce Synscapes -- a synthetic dataset for street scene parsing created using photorealistic rendering techniques, and show state-of-the-art results for training and validation as well as new types of analysis. We study the behavior…

The task of scene graph generation entails identifying object entities and their corresponding interaction predicates in a given image (or video). Due to the combinatorially large solution space, existing approaches to scene graph…

Creating scenes for captured motions that achieve realistic human-scene interaction is crucial for 3D animation in movies or video games. As character motion is often captured in a blue-screened studio without real furniture or objects in…

Three-dimensional scene generation holds significant potential in gaming, film, and virtual reality. However, most existing methods adopt a single-step generation process, making it difficult to balance scene complexity with minimal user…

Scene classification, aiming at classifying a scene image to one of the predefined scene categories by comprehending the entire image, is a longstanding, fundamental and challenging problem in computer vision. The rise of large-scale…

Extracting lane topology from perspective views (PV) is crucial for planning and control in autonomous driving. This approach extracts potential drivable trajectories for self-driving vehicles without relying on high-definition (HD) maps.…

To identify the location of objects of a particular class, a passive computer vision system generally processes all the regions in an image to finally output few regions. However, we can use structure in the scene to search for objects…

We propose UniSeg3D, a unified 3D scene understanding framework that achieves panoptic, semantic, instance, interactive, referring, and open-vocabulary segmentation tasks within a single model. Most previous 3D segmentation approaches are…

Seq2seq models have been shown to struggle with compositional generalisation, i.e. generalising to new and potentially more complex structures than seen during training. Taking inspiration from grammar-based models that excel at…

Visual scenes are composed of visual concepts and have the property of combinatorial explosion. An important reason for humans to efficiently learn from diverse visual scenes is the ability of compositional perception, and it is desirable…

We present a framework for efficient inference in structured image models that explicitly reason about objects. We achieve this by performing probabilistic inference using a recurrent neural network that attends to scene elements and…

The dominant approach to sequence generation is to produce a sequence in some predefined order, e.g. left to right. In contrast, we propose a more general model that can generate the output sequence by inserting tokens in any arbitrary…

Recurrent feedback connections in the mammalian visual system have been hypothesized to play a role in synthesizing input in the theoretical framework of analysis by synthesis. The comparison of internally synthesized representation with…