TIMI: Training-Free Image-to-3D Multi-Instance Generation with Spatial Fidelity

• URL: http://arxiv.org/abs/2603.01371v1
• Date: Mon, 02 Mar 2026 02:10:28 GMT
• Title: TIMI: Training-Free Image-to-3D Multi-Instance Generation with Spatial Fidelity
• Abstract summary: We propose a Training-free framework for Image-to-3D Multi-Instance generation that achieves high spatial fidelity.<n>Specifically, we first introduce an Instance-aware Separation Guidance (ISG) module, which facilitates instance disentanglement.<n>We then devise a Spatial-adaptive Geometry-stabilized Update (SGU) module that promotes the preservation of the geometric characteristics of instances.
• Score: 126.89088014048001
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Precise spatial fidelity in Image-to-3D multi-instance generation is critical for downstream real-world applications. Recent work attempts to address this by fine-tuning pre-trained Image-to-3D (I23D) models on multi-instance datasets, which incurs substantial training overhead and struggles to guarantee spatial fidelity. In fact, we observe that pre-trained I23D models already possess meaningful spatial priors, which remain underutilized as evidenced by instance entanglement issues. Motivated by this, we propose TIMI, a novel Training-free framework for Image-to-3D Multi-Instance generation that achieves high spatial fidelity. Specifically, we first introduce an Instance-aware Separation Guidance (ISG) module, which facilitates instance disentanglement during the early denoising stage. Next, to stabilize the guidance introduced by ISG, we devise a Spatial-stabilized Geometry-adaptive Update (SGU) module that promotes the preservation of the geometric characteristics of instances while maintaining their relative relationships. Extensive experiments demonstrate that our method yields better performance in terms of both global layout and distinct local instances compared to existing multi-instance methods, without requiring additional training and with faster inference speed.

Related papers

• Guiding Image-to-3D Generation with Test-Time Partial Observations [10.438161423840938]
  We introduce a training-free framework for incorporating partial geometric observations into pretrained image-to-3D generative models without retraining or finetuning.<n>Our results demonstrate that pretrained image-to-3D models can effectively integrate partial geometric observations through explicit test-time guidance.
  arXiv  Detail & Related papers  (2026-09-09T17:58:04Z)
• Flow3D-OPD: Multi-Teacher On-Policy Distillation for 3D Geometry Generation with Flow-Matching Diffusion Transformer [26.474560149220917]
  We propose textbfFlow3D-OPD, a two-stage post-training framework for 3D geometry generation.<n>In the first stage, we utilize the semi-policy to enhance the foundational capability of the pretrained model.<n>In the second stage, we consolidate heterogeneous expertise into a unified student model.
  arXiv  Detail & Related papers  (2026-09-07T07:36:52Z)
• SpatialFusion: Endowing Unified Image Generation with Intrinsic 3D Geometric Awareness [62.38746300197673]
  We propose a novel framework that internalizes 3D geometric awareness into unified image generation models.<n>Specifically, we first employ a Mixture-of-Transformers (MoT) architecture to augment the MLLM with a parallel spatial transformer.<n>By sharing self-attention with the MLLM, the spatial transformer learns to derive metric-depth maps of target images from rich semantic contexts.<n>These explicit geometric scaffolds are then injected into the diffusion backbone through a specialized depth adapter.
  arXiv  Detail & Related papers  (2026-04-29T06:46:59Z)
• Repurposing Geometric Foundation Models for Multi-view Diffusion [54.65956050951508]
  We propose a framework that repurposes the geometrically consistent feature space of geometric foundation models as the latent space for multi-view diffusion.<n>Our experiments demonstrate that GLD outperforms both VAE and RAE on 2D image quality and 3D consistency metrics, while accelerating training by more than 4.4x compared to the VAE latent space.
  arXiv  Detail & Related papers  (2026-03-23T17:57:05Z)
• RAYNOVA: Scale-Temporal Autoregressive World Modeling in Ray Space [51.441415833480505]
  RAYNOVA is a multiview world model for driving scenarios that employs a dual-causal autoregressive framework.<n>It constructs an isotropic-temporal representation across views, frames, and scales based on relative Plcker-ray positional encoding.
  arXiv  Detail & Related papers  (2026-02-24T08:41:40Z)
• GACO-CAD: Geometry-Augmented and Conciseness-Optimized CAD Model Generation from Single Image [11.612167656421079]
  Multi-modal large language models (MLLMs) still struggle with accurately inferring 3D geometry from 2D images.<n>We introduce GACO-CAD, a novel two-stage post-training framework.<n>Experiments on the DeepCAD and Fusion360 datasets show that GACO-CAD achieves state-of-the-art performance.
  arXiv  Detail & Related papers  (2025-10-20T04:57:20Z)
• SPFSplatV2: Efficient Self-Supervised Pose-Free 3D Gaussian Splatting from Sparse Views [18.814209805277503]
  SPFSplatV2, an efficient feed-forward framework for 3D Gaussian splatting from sparse multi-view images, is presented.<n>Method achieves state-of-the-art performance in both in-domain and out-of-domain novel view synthesis.
  arXiv  Detail & Related papers  (2025-09-21T21:37:56Z)
• TrackAny3D: Transferring Pretrained 3D Models for Category-unified 3D Point Cloud Tracking [25.788917457593673]
  TrackAny3D is the first framework to transfer large-scale pretrained 3D models for category-agnostic 3D SOT.<n>MoGE architecture adaptively activates specialized 3works based on distinct geometric characteristics.<n>Experiments show that TrackAny3D establishes new state-of-the-art performance on category-agnostic 3D SOT.
  arXiv  Detail & Related papers  (2025-07-26T10:41:55Z)
• Zero-shot Inexact CAD Model Alignment from a Single Image [53.37898107159792]
  A practical approach to infer 3D scene structure from a single image is to retrieve a closely matching 3D model from a database and align it with the object in the image.<n>Existing methods rely on supervised training with images and pose annotations, which limits them to a narrow set of object categories.<n>We propose a weakly supervised 9-DoF alignment method for inexact 3D models that requires no pose annotations and generalizes to unseen categories.
  arXiv  Detail & Related papers  (2025-07-04T04:46:59Z)
• UniPre3D: Unified Pre-training of 3D Point Cloud Models with Cross-Modal Gaussian Splatting [64.31900521467362]
  No existing pre-training method is equally effective for both object- and scene-level point clouds.<n>We introduce UniPre3D, the first unified pre-training method that can be seamlessly applied to point clouds of any scale and 3D models of any architecture.
  arXiv  Detail & Related papers  (2025-06-11T17:23:21Z)
• LTM3D: Bridging Token Spaces for Conditional 3D Generation with Auto-Regressive Diffusion Framework [40.17218893870908]
  LTM3D is a Latent Token space Modeling framework for conditional 3D shape generation.<n>It integrates the strengths of diffusion and auto-regressive (AR) models.<n>LTM3D offers a generalizable framework for multi-modal, multi-representation 3D generation.
  arXiv  Detail & Related papers  (2025-05-30T06:08:45Z)
• On Geometry-Enhanced Parameter-Efficient Fine-Tuning for 3D Scene Segmentation [52.96632954620623]
  We introduce a novel geometry-aware PEFT module specifically designed for 3D point cloud transformers.<n>Our approach sets a new benchmark for efficient, scalable, and geometry-aware fine-tuning of large-scale 3D point cloud models.
  arXiv  Detail & Related papers  (2025-05-28T15:08:36Z)
• GeoLRM: Geometry-Aware Large Reconstruction Model for High-Quality 3D Gaussian Generation [65.33726478659304]
  We introduce the Geometry-Aware Large Reconstruction Model (GeoLRM), an approach which can predict high-quality assets with 512k Gaussians and 21 input images in only 11 GB GPU memory. Previous works neglect the inherent sparsity of 3D structure and do not utilize explicit geometric relationships between 3D and 2D images. GeoLRM tackles these issues by incorporating a novel 3D-aware transformer structure that directly processes 3D points and uses deformable cross-attention mechanisms.
  arXiv  Detail & Related papers  (2024-06-21T17:49:31Z)
• StableDreamer: Taming Noisy Score Distillation Sampling for Text-to-3D [88.66678730537777]
  We present StableDreamer, a methodology incorporating three advances. First, we formalize the equivalence of the SDS generative prior and a simple supervised L2 reconstruction loss. Second, our analysis shows that while image-space diffusion contributes to geometric precision, latent-space diffusion is crucial for vivid color rendition.
  arXiv  Detail & Related papers  (2023-12-02T02:27:58Z)
• Learning Versatile 3D Shape Generation with Improved AR Models [91.87115744375052]
  Auto-regressive (AR) models have achieved impressive results in 2D image generation by modeling joint distributions in the grid space. We propose the Improved Auto-regressive Model (ImAM) for 3D shape generation, which applies discrete representation learning based on a latent vector instead of volumetric grids.
  arXiv  Detail & Related papers  (2023-03-26T12:03:18Z)
• GLASS: Geometric Latent Augmentation for Shape Spaces [28.533018136138825]
  We use geometrically motivated energies to augment and thus boost a sparse collection of example (training) models. We analyze the Hessian of the as-rigid-as-possible (ARAP) energy to sample from and project to the underlying (local) shape space. We present multiple examples of interesting and meaningful shape variations even when starting from as few as 3-10 training shapes.
  arXiv  Detail & Related papers  (2021-08-06T17:56:23Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.