We introduce ReRef-3D, a benchmark for language-guided placement in 3D scenes. It contains 33,826 instructions across 998 CLEVR-derived scenes, spanning 16 placement families and direct, one-hop, and two-hop references. Each instruction must be resolved into a valid new placement position. Given that an instruction defines a region of acceptable placements rather than one coordinate, our evaluation inserts a prediction into the scene, recomputes relations, and tests relation satisfaction and physical validity. Each instruction also includes a verified naturalized rewrite. After fine-tuning, LLaVA-3D, 3D-LLM, and PlaceIt3D produce valid placements for 68.3%, 31.6%, and 22.4% of instructions, respectively. Across models, relation satisfaction surpasses physical validity, relations such as nearest and between are the most difficult, and phrasing has minimal effect on performance.
Neural 3D scene editing is often evaluated by semantic alignment alone, although a convincing result may alter unrelated content or become inconsistent across views. We introduce EditBench3D, a representation-agnostic benchmark that treats editing as controlled information replacement. It evaluates four complementary p...
OmniMech is introduced, the first million-scale benchmark for evaluating VLMs on executable CAD generation from industrial manufacturing data, and experiments show that current VLMs and CAD-specialized models still struggle with executable program synthesis, fine-grained 3D reconstruction, and reliable enforcement of d...
Tai-Ting Lu, Run-Ze Liu, Zi-Wei Dong et al.· 0 citations
SceneBench is introduced, a benchmark of 966 photorealistic 3D scenes reconstructed with Gaussian Splatting and densely annotated with hierarchical semantics spanning scenes, rooms, functional areas, object groups, and individual objects that provides a realistic testbed for developing and evaluating models capable of...
Anubhav Khanal, Prabigya Acharya, Roshni Poudel et al.· 0 citations
A unified multi-axis taxonomy is introduced that enables us to classify the available methods in 3D Gaussian splatting methods in terms of five complementary categories: semantic vocabulary space, representation form, functional role, knowledge source, and query mechanism.
Editable 3D scene creation requires object instances and lights that can be inspected, moved, and imported into standard engines, yet existing single-image methods largely stop at room-scale geometry, baked/global illumination, or text-driven generation. We introduce Lumera (Light-aware Unified Engine-native Reconstruc...
This work presents a graph-based intermediate representation that separates semantic coherence from physical feasibility, together with a hybrid search-and-refinement strategy that moves layout generation beyond local relational modeling and initialization-sensitive optimization toward globally consistent reasoning and...
Jia-Lu Huang, Yingxuan You, Fei Wang et al.· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
