Right Side Up? Disentangling Orientation Understanding in MLLMs with Fine-grained Multi-axis Perception Tasks

• URL: http://arxiv.org/abs/2505.21649v4
• Date: Wed, 04 Jun 2025 17:28:29 GMT
• Title: Right Side Up? Disentangling Orientation Understanding in MLLMs with Fine-grained Multi-axis Perception Tasks
• Authors: Keanu Nichols, Nazia Tasnim, Yuting Yan, Nicholas Ikechukwu, Elva Zou, Deepti Ghadiyaram, Bryan A. Plummer,
• Abstract summary: We introduce DORI (Discriminative Orientation Reasoning Intelligence), a benchmark establishing object orientation perception as a primary evaluation target.<n>DORI assesses four dimensions of orientation comprehension: frontal alignment, rotational transformations, relative directional relationships, and canonical orientation understanding.<n>Our evaluation of 15 state-of-the-art vision-language models reveals critical limitations.<n>DORI offers implications for improving robotic control, 3D scene reconstruction, and human-AI interaction in physical environments.
• Score: 17.357441373079382
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Object orientation understanding represents a fundamental challenge in visual perception critical for applications like robotic manipulation and augmented reality. Current vision-language benchmarks fail to isolate this capability, often conflating it with positional relationships and general scene understanding. We introduce DORI (Discriminative Orientation Reasoning Intelligence), a comprehensive benchmark establishing object orientation perception as a primary evaluation target. DORI assesses four dimensions of orientation comprehension: frontal alignment, rotational transformations, relative directional relationships, and canonical orientation understanding. Through carefully curated tasks from 11 datasets spanning 67 object categories across synthetic and real-world scenarios, DORI provides insights on how multi-modal systems understand object orientations. Our evaluation of 15 state-of-the-art vision-language models reveals critical limitations: even the best models achieve only 54.2% accuracy on coarse tasks and 33.0% on granular orientation judgments, with performance deteriorating for tasks requiring reference frame shifts or compound rotations. These findings demonstrate the need for dedicated orientation representation mechanisms, as models show systematic inability to perform precise angular estimations, track orientation changes across viewpoints, and understand compound rotations - suggesting limitations in their internal 3D spatial representations. As the first diagnostic framework specifically designed for orientation awareness in multimodal systems, DORI offers implications for improving robotic control, 3D scene reconstruction, and human-AI interaction in physical environments. DORI data: https://huggingface.co/datasets/appledora/DORI-Benchmark

Related papers

• VisualTrans: A Benchmark for Real-World Visual Transformation Reasoning [10.497961559068493]
  Visual transformation reasoning (VTR) is a vital cognitive capability that empowers intelligent agents to understand dynamic scenes.<n>Existing benchmarks suffer from a sim-to-real gap, limited task complexity, and incomplete reasoning coverage.<n>VisualTrans is the first comprehensive benchmark specifically designed for VTR in real-world human-object interaction scenarios.
  arXiv  Detail & Related papers  (2025-08-06T03:07:05Z)
• EOC-Bench: Can MLLMs Identify, Recall, and Forecast Objects in an Egocentric World? [52.99661576320663]
  multimodal large language models (MLLMs) have driven breakthroughs in egocentric vision applications.<n>EOC-Bench is an innovative benchmark designed to systematically evaluate object-centric embodied cognition in dynamic egocentric scenarios.<n>We conduct comprehensive evaluations of various proprietary, open-source, and object-level MLLMs based on EOC-Bench.
  arXiv  Detail & Related papers  (2025-06-05T17:44:12Z)
• SoFar: Language-Grounded Orientation Bridges Spatial Reasoning and Object Manipulation [49.858348469657784]
  We introduce the concept of semantic orientation, which defines object orientations using natural language in a reference-frame-free manner.<n>By integrating semantic orientation into a VLM system, we enable robots to generate manipulation actions with both positional and orientational constraints.
  arXiv  Detail & Related papers  (2025-02-18T18:59:02Z)
• Orient Anything: Learning Robust Object Orientation Estimation from Rendering 3D Models [79.96917782423219]
  Orient Anything is the first expert and foundational model designed to estimate object orientation in a single image.<n>By developing a pipeline to annotate the front face of 3D objects, we collect 2M images with precise orientation annotations.<n>Our model achieves state-of-the-art orientation estimation accuracy in both rendered and real images.
  arXiv  Detail & Related papers  (2024-12-24T18:58:43Z)
• Is 'Right' Right? Enhancing Object Orientation Understanding in Multimodal Large Language Models through Egocentric Instruction Tuning [7.911608620021529]
  Multimodal large language models (MLLMs) act as essential interfaces, connecting humans with AI technologies in multimodal applications.<n>Current MLLMs face challenges in accurately interpreting object orientation in images due to inconsistent orientation annotations in training data.<n>We propose egocentric instruction tuning, which aligns MLLMs' orientation understanding with the user's perspective.
  arXiv  Detail & Related papers  (2024-11-24T15:07:47Z)
• GRA: Detecting Oriented Objects through Group-wise Rotating and Attention [64.21917568525764]
  Group-wise Rotating and Attention (GRA) module is proposed to replace the convolution operations in backbone networks for oriented object detection. GRA can adaptively capture fine-grained features of objects with diverse orientations, comprising two key components: Group-wise Rotating and Group-wise Attention. GRA achieves a new state-of-the-art (SOTA) on the DOTA-v2.0 benchmark, while saving the parameters by nearly 50% compared to the previous SOTA method.
  arXiv  Detail & Related papers  (2024-03-17T07:29:32Z)
• Learning Fine-grained View-Invariant Representations from Unpaired Ego-Exo Videos via Temporal Alignment [71.16699226211504]
  We propose to learn fine-grained action features that are invariant to the viewpoints by aligning egocentric and exocentric videos in time. To this end, we propose AE2, a self-supervised embedding approach with two key designs. For evaluation, we establish a benchmark for fine-grained video understanding in the ego-exo context.
  arXiv  Detail & Related papers  (2023-06-08T19:54:08Z)
• Knowing Earlier what Right Means to You: A Comprehensive VQA Dataset for Grounding Relative Directions via Multi-Task Learning [16.538887534958555]
  We introduce GRiD-A-3D, a novel diagnostic visual question-answering dataset based on abstract objects. Our dataset allows for a fine-grained analysis of end-to-end VQA models' capabilities to ground relative directions. We demonstrate that within a few epochs, the subtasks required to reason over relative directions are learned in the order in which relative directions are intuitively processed.
  arXiv  Detail & Related papers  (2022-07-06T12:31:49Z)
• Learning Oriented Remote Sensing Object Detection via Naive Geometric Computing [38.508709334835316]
  We propose a mechanism that learns the regression of horizontal proposals, oriented proposals, and rotation angles of objects in a consistent manner. Our proposed idea is simple and intuitive that can be readily implemented.
  arXiv  Detail & Related papers  (2021-12-01T13:58:42Z)
• Benchmarking Unsupervised Object Representations for Video Sequences [111.81492107649889]
  We compare the perceptual abilities of four object-centric approaches: ViMON, OP3, TBA and SCALOR. Our results suggest that the architectures with unconstrained latent representations learn more powerful representations in terms of object detection, segmentation and tracking. Our benchmark may provide fruitful guidance towards learning more robust object-centric video representations.
  arXiv  Detail & Related papers  (2020-06-12T09:37:24Z)

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.